© 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. 97672
    Prev
    Next
    INDEX
    Explanations

    code/identifiers

    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
     Monfieur
    -0.85
     myſelf
    -0.82
     greateſt
    -0.78
     uſe
    -0.77
     Efq
    -0.77
    itary
    -0.76
     houſe
    -0.76
     faſt
    -0.76
     pleaſure
    -0.76
     Chriftian
    -0.73
    POSITIVE LOGITS
     kaynağından
    0.65
    MLLoader
    0.62
    ScopeManager
    0.60
     =>
    0.59
    SourceChecksum
    0.59
     CreateTagHelper
    0.58
    HomeAsUpEnabled
    0.58
     MainAxisSize
    0.57
    ">//
    0.57
    addPreferredGap
    0.56
    Activations Density 0.182%

    No Known Activations