© 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. 0-CLT-HP
    7. 41822
    Prev
    Next
    INDEX
    Explanations

    models/types

    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
     ModelExpression
    -1.08
     itſelf
    -0.98
     myſelf
    -0.97
     houſe
    -0.93
    WebVitals
    -0.88
    StructEnd
    -0.84
     ſche
    -0.83
     purpoſe
    -0.83
     Efq
    -0.83
     perfons
    -0.81
    POSITIVE LOGITS
     
    0.55
     and
    0.46
     not
    0.43
     wel
    0.43
     so
    0.42
    ,
    0.42
     (
    0.42
     sa
    0.41
     “
    0.41
     On
    0.41
    Activations Density 0.323%

    No Known Activations