© 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. 5492
    Prev
    Next
    INDEX
    Explanations

    business acronyms and names related to legal cases

    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
    1053
    +0.15
    0.6%
    78
    +0.14
    0.6%
    61
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.15
    0.03
    1053
    +0.14
    0.03
    1406
    +0.13
    0.04
    Negative Logits
    jednoc
    -0.64
    OGND
    -0.61
    nowu
    -0.55
    rlrl
    -0.54
    espół
    -0.52
    awsze
    -0.51
    tehen
    -0.46
     PeEnEo
    -0.43
    PhysRevLett
    -0.43
    semaphore
    -0.42
    POSITIVE LOGITS
     CR
    1.08
     cr
    1.08
     Cr
    1.07
    Cr
    1.01
    cr
    0.95
    CR
    0.94
     CRI
    0.90
     cre
    0.88
     Cri
    0.88
     cri
    0.87
    Activations Density 0.233%

    No Known Activations