© 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. 5-CLT-HP
    7. 1053
    Prev
    Next
    INDEX
    Explanations

    entering

    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
    Portály
    -0.50
    uestamente
    -0.48
    pexpr
    -0.47
    ρίες
    -0.47
    ']").
    -0.46
    umpulan
    -0.44
    ']->
    -0.44
    Esper
    -0.44
    shows
    -0.43
    apyrus
    -0.41
    POSITIVE LOGITS
     continúas
    0.63
     room
    0.63
    openSession
    0.63
    SourceChecksum
    0.59
    addPreferredGap
    0.57
    GeneratedMessage
    0.57
    Хро
    0.56
     scene
    0.55
    RenderAtEndOf
    0.55
    ArgsConstructor
    0.53
    Activations Density 0.006%

    No Known Activations