© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1166
    Prev
    Next
    INDEX
    Explanations

    observe

    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
    //
    -0.67
    RTLD
    -0.58
    PhysRev
    -0.55
    RepeatedField
    -0.52
    gini
    -0.50
    transQ
    -0.50
    expandindo
    -0.50
    UpInside
    -0.50
    isContained
    -0.49
    topf
    -0.48
    POSITIVE LOGITS
    aarrggbb
    0.73
     Silence
    0.68
     silence
    0.60
    ponente
    0.54
    absolute
    0.54
     Discretion
    0.51
     strict
    0.51
    Sila
    0.51
     strictest
    0.50
     absolute
    0.50
    Activations Density 0.003%

    No Known Activations