© 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. 5-CLT-HP
    7. 95122
    Prev
    Next
    INDEX
    Explanations

    and/of

    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
    MemoryWarning
    -0.49
    ();)
    -0.47
    waitKey
    -0.45
    Gweler
    -0.45
    Népesség
    -0.43
    withOpacity
    -0.43
    पया
    -0.42
     of
    -0.42
     corrobor
    -0.41
     Normdatei
    -0.41
    POSITIVE LOGITS
    TagMode
    0.69
     متعلقه
    0.68
    GOTREF
    0.59
    WindowConstants
    0.57
    SourceChecksum
    0.56
     geze
    0.56
     Mammals
    0.53
    setVerticalGroup
    0.53
    pushFollow
    0.53
     Metals
    0.52
    Activations Density 0.002%

    No Known Activations