© 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. 1087
    Prev
    Next
    INDEX
    Explanations

    info

    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
    Info
    -1.23
     Info
    -1.21
     info
    -1.16
    info
    -1.06
    INFO
    -0.87
     INFO
    -0.84
    DoubleQuotes
    -0.72
     informasi
    -0.61
    s
    -0.60
    esgue
    -0.59
    POSITIVE LOGITS
     Roskov
    0.59
    Enllaces
    0.58
    hoots
    0.58
    anskje
    0.57
    IntoConstraints
    0.56
    тего
    0.54
     مشين
    0.54
    条
    0.54
    PreInfinity
    0.52
    Pautan
    0.51
    Activations Density 0.147%

    No Known Activations