© 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. 733
    Prev
    Next
    INDEX
    Explanations

    code and German text

    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
    AndEndTag
    -0.70
    ftagPool
    -0.69
    SequentialGroup
    -0.61
    UnitTesting
    -0.58
    TintMode
    -0.57
    WindowConstants
    -0.57
     CURIAM
    -0.57
    <()>
    -0.55
    ochim
    -0.55
    WaitGroup
    -0.54
    POSITIVE LOGITS
    sta
    0.54
    st
    0.53
    MessageOf
    0.52
    esta
    0.48
    estas
    0.48
     a
    0.48
     <<<
    0.46
     nắm
    0.45
    hor
    0.45
    STA
    0.45
    Activations Density 0.004%

    No Known Activations