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

    Neuronpedia

    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. 7069
    Prev
    Next
    INDEX
    Explanations

    phrases related to concealing actions or objects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    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
    468
    +0.12
    0.4%
    1892
    +0.12
    0.4%
    976
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.12
    0.03
    1892
    +0.12
    0.03
    851
    +0.12
    0.03
    Negative Logits
    AMILTON
    -0.58
    efty
    -0.56
     vorrei
    -0.53
    UAWEI
    -0.52
     esercit
    -0.50
     arric
    -0.49
    solicited
    -0.46
    ickory
    -0.45
     farlo
    -0.45
    asmussen
    -0.44
    POSITIVE LOGITS
     hide
    1.19
     hidden
    1.12
    hide
    1.09
     hiding
    1.07
     hides
    1.06
     Hide
    1.05
    hidden
    0.98
     hid
    0.98
    Hide
    0.95
    Hidden
    0.94
    Activations Density 0.086%

    No Known Activations