© 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. 40027
    Prev
    Next
    INDEX
    Explanations

    unic

    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
    unic
    -0.93
    tagHelperRunner
    -0.59
     Lips
    -0.59
     informée
    -0.52
     enca
    -0.51
    مصادر
    -0.50
    וויק
    -0.49
    yttö
    -0.48
    Mon
    -0.47
    UNIC
    -0.46
    POSITIVE LOGITS
     referenties
    0.71
    kháu
    0.69
    PERTIES
    0.67
    المناصب
    0.63
    SPATH
    0.63
    ophysics
    0.62
     QWidget
    0.61
    ourtney
    0.61
     ["",
    0.59
    mybatisplus
    0.59
    Activations Density 0.061%

    No Known Activations