© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3496
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Walkover
    -0.77
    ghijklmnop
    -0.77
    égias
    -0.71
     становника
    -0.69
    TypedDataSet
    -0.69
    ]--;
    -0.68
    những
    -0.68
    XMLSchema
    -0.67
    các
    -0.67
    dtos
    -0.66
    POSITIVE LOGITS
    исленность
    0.60
     répé
    0.39
    prefixer
    0.38
     race
    0.36
    合わせ
    0.36
     épaules
    0.35
    </blockquote>
    0.34
     kabul
    0.34
    ReusableCell
    0.34
    .*")]
    0.33
    Activations Density 0.003%

    No Known Activations