© 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. 12262
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
    Similar
    -1.00
     Similar
    -0.73
    similar
    -0.56
     similar
    -0.54
    tour
    -0.54
    intenant
    -0.53
    Архівовано
    -0.51
     ơn
    -0.50
    adpleegd
    -0.48
     betweenstory
    -0.47
    POSITIVE LOGITS
    complexContent
    0.70
    enderror
    0.69
    UserScript
    0.65
    MigrationBuilder
    0.62
    rungsseite
    0.60
     فريبيس
    0.59
    NameInMap
    0.59
    \{\\
    0.57
     виправивши
    0.57
    ContentAlignment
    0.56
    Activations Density 0.029%

    No Known Activations