© 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. 1011
    Prev
    Next
    INDEX
    Explanations

    months

    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
     Exactos
    -0.76
    basis
    -0.60
    تقاوى
    -0.60
     Infórmanos
    -0.59
    twas
    -0.59
     partagé
    -0.58
     partag
    -0.58
     of
    -0.57
    ubscribe
    -0.57
    ecap
    -0.56
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.48
    tvguidetime
    0.46
     صوتيه
    0.44
    IntoConstraints
    0.43
    <?,
    0.43
    (/\
    0.42
    uxxxx
    0.42
    InsertCommand
    0.42
     gta
    0.41
     bianchi
    0.41
    Activations Density 0.185%

    No Known Activations