© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90556
    Prev
    Next
    INDEX
    Explanations

    cius

    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
    hoeddwyd
    -0.72
    ResumeLayout
    -0.71
    opolis
    -0.68
    UnitTesting
    -0.65
    omock
    -0.65
     mucus
    -0.63
    LError
    -0.63
    ública
    -0.63
     downtown
    -0.62
     Heights
    -0.62
    POSITIVE LOGITS
    s
    0.78
    Personensuche
    0.58
    e
    0.57
    i
    0.52
    sides
    0.52
    ')}}">
    0.50
    y
    0.50
    ējās
    0.48
     nélkül
    0.48
    o
    0.48
    Activations Density 0.097%

    No Known Activations