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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95185
    Prev
    Next
    INDEX
    Explanations

    venue

    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
    İstinadlar
    -0.70
     للاسماء
    -0.70
    PreferredItem
    -0.68
    enment
    -0.64
    antiate
    -0.64
    cagon
    -0.64
     tel
    -0.61
     الحره
    -0.60
     BoxDecoration
    -0.59
    imba
    -0.59
    POSITIVE LOGITS
    able
    0.73
    a
    0.53
    ap
    0.52
    ably
    0.50
    ScopeManager
    0.47
    CodeAnalysis
    0.44
    apt
    0.43
     sép
    0.42
    IntoConstraints
    0.41
    cri
    0.40
    Activations Density 0.090%

    No Known Activations