© 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. 1-CLT-HP
    7. 12111
    Prev
    Next
    INDEX
    Explanations

    ism

    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
     épu
    -0.75
     feroit
    -0.73
     auroit
    -0.73
     fisuras
    -0.68
     samarbeid
    -0.67
     vété
    -0.65
     avoient
    -0.65
     pouvoit
    -0.65
     refroid
    -0.63
    клопе
    -0.62
    POSITIVE LOGITS
     Forum
    0.52
     systems
    0.50
     Torch
    0.49
     Turnpike
    0.47
     Trem
    0.46
    }{||
    0.46
     tsunami
    0.46
     Magnus
    0.45
     Trang
    0.45
     TRS
    0.45
    Activations Density 0.063%

    No Known Activations