© 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. 4535
    Prev
    Next
    INDEX
    Explanations

    description/creation

    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
    Mainly
    -0.58
     Mainly
    -0.57
     primarily
    -0.56
    primarily
    -0.55
     mainly
    -0.55
     Mostly
    -0.55
     main
    -0.54
     chiefly
    -0.53
    Mostly
    -0.52
    :]:
    -0.52
    POSITIVE LOGITS
     at
    0.81
     as
    0.74
     שוליים
    0.66
     for
    0.63
     unknowingly
    0.60
     virtually
    0.58
    bitField
    0.57
    PUESTA
    0.57
     informally
    0.56
     Virtually
    0.56
    Activations Density 0.010%

    No Known Activations