© 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. 3392
    Prev
    Next
    INDEX
    Explanations

    manicure

    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
    bootstrapcdn
    -0.63
    EDEFAULT
    -0.55
    +:+
    -0.53
     instead
    -0.52
    Демографія
    -0.50
    TagMode
    -0.50
     NSCoder
    -0.49
    ouwd
    -0.49
    rather
    -0.48
     Instead
    -0.48
    POSITIVE LOGITS
    DropColumn
    0.59
     taches
    0.56
    らかに
    0.54
     nakalista
    0.53
     desar
    0.52
     transfé
    0.51
    łko
    0.50
     dispositions
    0.48
     plots
    0.48
    onActivityResult
    0.48
    Activations Density 0.004%

    No Known Activations