© 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. 1-CLT-HP
    7. 14348
    Prev
    Next
    INDEX
    Explanations

    nucleosides

    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
    URLException
    -0.77
     defaultstate
    -0.75
    WithIOException
    -0.74
    gdx
    -0.73
    '))
    -0.72
    ]")]
    -0.71
    ".
    -0.70
    >");
    -0.70
    RenderAtEndOf
    -0.69
    $.
    -0.68
    POSITIVE LOGITS
     knock
    0.43
    Tembelea
    0.43
     Zub
    0.43
     escri
    0.42
    RectangleBorder
    0.41
    కు
    0.41
    ltä
    0.41
    paž
    0.40
    Knock
    0.40
     Madame
    0.40
    Activations Density 0.011%

    No Known Activations