© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45193
    Prev
    Next
    INDEX
    Explanations

    Description

    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
    serviceWorker
    -0.58
    onnaise
    -0.57
    letoe
    -0.56
    httphttps
    -0.55
    nosaurus
    -0.55
    dogs
    -0.53
    roads
    -0.53
     pname
    -0.53
    SourceChecksum
    -0.53
    <?,
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.54
    Чыганаклар
    0.53
     Winaray
    0.49
     كومونز
    0.49
    MessageTagHelper
    0.48
     насељу
    0.48
    endorff
    0.47
    toEqual
    0.46
    inheritDoc
    0.45
    aarrggbb
    0.44
    Activations Density 0.007%

    No Known Activations