© 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. 44010
    Prev
    Next
    INDEX
    Explanations

    autism

    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
     act
    -0.88
    act
    -0.62
    cers
    -0.59
     co
    -0.55
     CT
    -0.54
     E
    -0.54
     H
    -0.54
    AILED
    -0.53
    etheless
    -0.52
    Autism
    -0.52
    POSITIVE LOGITS
     feroit
    0.81
     figliu
    0.79
     heureuse
    0.75
     impegn
    0.74
    ThroughAttribute
    0.73
     élas
    0.73
    GraphicsUnit
    0.72
     itſelf
    0.71
     passés
    0.71
     comigo
    0.71
    Activations Density 0.043%

    No Known Activations