© 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. 4-CLT-HP
    7. 276
    Prev
    Next
    INDEX
    Explanations

    progression

    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
     ་་
    -0.67
    rzost
    -0.67
    ^(@)
    -0.66
    InputBorder
    -0.66
     itſelf
    -0.66
     cdti
    -0.65
    <bos>
    -0.65
    󠁧
    -0.64
     lenker
    -0.64
     فريبيس
    -0.64
    POSITIVE LOGITS
    .
    0.73
    time
    0.57
    Time
    0.55
    Personensuche
    0.51
     time
    0.50
     OR
    0.50
     Time
    0.49
    !
    0.49
    :
    0.49
     للاسماء
    0.49
    Activations Density 0.007%

    No Known Activations