© 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. 1-CLT-HP
    7. 45769
    Prev
    Next
    INDEX
    Explanations

    boundaries

    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
    findpost
    -0.77
    jsxFileName
    -0.76
    ⓧ
    -0.70
     تانيه
    -0.66
    ftagPool
    -0.65
    InjectAttribute
    -0.64
    thâu
    -0.62
    principalColumn
    -0.59
     Audiodateien
    -0.59
    EndContext
    -0.59
    POSITIVE LOGITS
     Gerais
    0.58
    Identyfik
    0.54
     LoggerFactory
    0.54
    sitis
    0.53
    ziała
    0.46
     Lauf
    0.46
     sapiens
    0.46
    mag
    0.45
     Cair
    0.44
    skjaer
    0.44
    Activations Density 0.089%

    No Known Activations