© 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. 716
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    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
    RenderAtEndOf
    -0.66
     GenerationType
    -0.63
    AutoScaleMode
    -0.63
    enterOuterAlt
    -0.61
    ///</
    -0.53
    none
    -0.50
    sizeCache
    -0.47
    </caption>
    -0.45
     façons
    -0.45
    orElseThrow
    -0.45
    POSITIVE LOGITS
    aarrggbb
    0.76
    jectures
    0.51
    onucle
    0.49
    őd
    0.49
    ביוגרפיה
    0.49
    แน่น
    0.49
     partnerships
    0.48
     Normalize
    0.48
    랫
    0.47
     hof
    0.47
    Activations Density 0.020%

    No Known Activations