© 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. 0-CLT-HP
    7. 43157
    Prev
    Next
    INDEX
    Explanations

    how

    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
     how
    -1.73
    how
    -1.63
     bagaimana
    -1.31
    How
    -1.29
     cómo
    -1.27
     hvordan
    -1.23
     How
    -1.18
    HOW
    -1.13
     miten
    -1.06
     hogyan
    -1.00
    POSITIVE LOGITS
     much
    1.02
    ReusableCell
    1.00
     to
    0.91
     you
    0.77
    bootstrapcdn
    0.76
     well
    0.71
    much
    0.71
    enumi
    0.68
     dAtA
    0.67
     المعيارى
    0.66
    Activations Density 0.142%

    No Known Activations