© 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 EvalsExportsinterp-engineNEWAPI 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. 14909
    Prev
    Next
    INDEX
    Explanations

    mentions of ballot-related terms, likely related to elections and voting

    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
    889
    +0.23
    1.0%
    204
    +0.20
    0.9%
    1757
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.23
    0.04
    889
    +0.20
    0.04
    227
    +0.14
    0.06
    Negative Logits
     كومونز
    -0.64
     Himo
    -0.61
    fontName
    -0.60
    EndInit
    -0.58
    PerformLayout
    -0.57
    styleType
    -0.57
    Fö
    -0.56
     kosme
    -0.54
    Tél
    -0.53
    Ӧ
    -0.53
    POSITIVE LOGITS
     🤣🤣
    0.84
     unspeak
    0.84
     rval
    0.83
     laft
    0.82
     :'(
    0.81
     pegasus
    0.81
     thut
    0.81
     pixar
    0.81
     intersper
    0.80
     indescri
    0.80
    Activations Density 0.432%

    No Known Activations