© 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. 5-CLT-HP
    7. 3903
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    TagMode
    -0.57
    httphttps
    -0.55
    Requ
    -0.54
    प्
    -0.52
     Requ
    -0.49
    CGRectMake
    -0.47
     Komisi
    -0.47
    xnn
    -0.46
    reness
    -0.45
     Measuring
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.73
    OGND
    0.61
     narrowed
    0.60
    SourceChecksum
    0.57
     narrows
    0.56
    Personendaten
    0.54
    метров
    0.53
     in
    0.53
     narrowing
    0.52
    Narrow
    0.52
    Activations Density 0.001%

    No Known Activations