© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    surgery

    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
     even
    -0.54
     almost
    -0.48
     consistently
    -0.47
    UnknownFields
    -0.46
     when
    -0.44
     Almost
    -0.43
     properly
    -0.43
    得
    -0.43
     especially
    -0.42
     untrained
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.85
    UrlResolution
    0.73
    hematical
    0.70
     kaarangay
    0.69
    ]--;
    0.68
     nahilalakip
    0.66
    VolleyError
    0.64
    MemoryWarning
    0.63
    verständlich
    0.62
    ValueStyle
    0.61
    Activations Density 0.006%

    No Known Activations