© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14752
    Prev
    Next
    INDEX
    Explanations

    references to long-term situations or contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    It responds to the word "long" (including hyphenated compounds like "long-term" or "long-awaited"), i.e., expressions indicating long duration.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    900
    +0.14
    0.5%
    297
    +0.12
    0.4%
    370
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    900
    +0.14
    0.07
    1026
    +0.12
    0.06
    370
    +0.12
    0.06
    Negative Logits
    conio
    -0.56
     PLWABN
    -0.53
    hdysval
    -0.49
    Economia
    -0.49
     rask
    -0.46
    getchar
    -0.46
    ddots
    -0.46
    ++){
    -0.45
    ApiModel
    -0.45
    DisplayMetrics
    -0.45
    POSITIVE LOGITS
     LONG
    1.08
    long
    1.05
     long
    1.04
     Long
    1.03
     longs
    1.00
    Long
    0.99
    LONG
    0.97
    getLong
    0.87
     indestru
    0.84
    setLong
    0.82
    Activations Density 0.124%

    No Known Activations