© 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. 1-CLT-HP
    7. 14896
    Prev
    Next
    INDEX
    Explanations

    fib/ker

    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
    ker
    -0.71
    KER
    -0.64
     ker
    -0.48
     Neptune
    -0.47
     BufferedReader
    -0.47
     bauer
    -0.46
    EnableWeb
    -0.46
     pumping
    -0.46
     TAP
    -0.45
     LCD
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.73
    elemField
    0.69
    MarshalTo
    0.67
     незавершена
    0.63
    AutoScaleMode
    0.60
    complexType
    0.60
     createSprite
    0.60
    发表于
    0.60
    примеча
    0.59
    Newswire
    0.58
    Activations Density 0.022%

    No Known Activations