© 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. Gemma-2-2B
    5. 0-CLT-HP
    7. 94783
    Prev
    Next
    INDEX
    Explanations

    scientific research and patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.63
    !
    -0.55
    ↵
    -0.53
    4
    -0.52
    ,
    -0.51
    <bos>
    -0.51
    ..
    -0.50
    <eos>
    -0.49
    2
    -0.49
    5
    -0.49
    POSITIVE LOGITS
    ^(@)
    0.94
    ]='\
    0.94
    GeoNames
    0.94
    esterday
    0.93
     Theſe
    0.91
     nahilalakip
    0.91
    ⓧ
    0.90
     Jefus
    0.90
    ]--;
    0.87
    styleType
    0.86
    Activations Density 0.591%

    No Known Activations