© 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. 43053
    Prev
    Next
    INDEX
    Explanations

    ation

    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
    ation
    -3.56
    ATION
    -2.31
    ations
    -1.41
    ationen
    -1.05
    ación
    -1.02
    tion
    -0.84
    ATIONS
    -0.84
    ेशन
    -0.83
     ation
    -0.77
    ated
    -0.76
    POSITIVE LOGITS
     InputDecoration
    1.34
    featureID
    1.33
    MigrationBuilder
    1.31
    EDEFAULT
    1.29
    BeginContext
    1.28
     виправивши
    1.25
    AndEndTag
    1.22
    zzleHttp
    1.19
    \{\\
    1.17
     nahilalakip
    1.17
    Activations Density 0.665%

    No Known Activations