© 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. 4-CLT-HP
    7. 3342
    Prev
    Next
    INDEX
    Explanations

    сколько

    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
     resourceCulture
    -0.77
    IBarButtonItem
    -0.77
    Personendaten
    -0.76
    Παραπομπές
    -0.74
    tvguidetime
    -0.73
    twimg
    -0.73
    GEBURTSDATUM
    -0.72
    XmlAccessorType
    -0.70
    AnchorStyles
    -0.69
    ConstraintMaker
    -0.69
    POSITIVE LOGITS
     time
    0.76
     money
    0.68
     we
    0.67
     effort
    0.67
     energy
    0.66
     weight
    0.64
     importance
    0.63
     investors
    0.63
     customers
    0.63
     scientists
    0.61
    Activations Density 0.006%

    No Known Activations