© 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. 349
    Prev
    Next
    INDEX
    Explanations

    om

    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
    تقاوى
    -1.00
     الاطلاع
    -0.81
    ValueStyle
    -0.75
    WriteBarrier
    -0.73
    setVerticalGroup
    -0.66
    bootstrapcdn
    -0.65
     سكانية
    -0.63
    LookAnd
    -0.62
    ReusableCell
    -0.61
    Enllaces
    -0.61
    POSITIVE LOGITS
    alie
    0.53
    alik
    0.46
    ander
    0.45
     Blau
    0.45
     Koran
    0.44
    kå
    0.44
    alous
    0.43
    olk
    0.43
    Polly
    0.42
    áli
    0.42
    Activations Density 0.008%

    No Known Activations