© 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. 5-CLT-HP
    7. 4686
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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
     or
    -0.56
    ish
    -0.47
     cố
    -0.45
     more
    -0.45
    less
    -0.43
    /
    -0.42
    ard
    -0.42
    (
    -0.42
    ниями
    -0.42
    hurst
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    )++;
    0.68
    nologue
    0.67
    <caption>
    0.66
     well
    0.65
    /**
    0.65
    #
    0.64
    +:+
    0.63
    Kariera
    0.63
     StatefulWidget
    0.63
    Activations Density 0.002%

    No Known Activations