© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95571
    Prev
    Next
    INDEX
    Explanations

    asi

    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
    Negative Logits
    asi
    -1.21
    ASI
    -0.82
     CreateTagHelper
    -0.58
    Zeneca
    -0.52
    etlen
    -0.52
    statt
    -0.49
    معلومات
    -0.48
    ModelSerializer
    -0.48
     BorderRadius
    -0.47
     begging
    -0.47
    POSITIVE LOGITS
     ©️
    0.63
     wireType
    0.62
    migrationBuilder
    0.59
    InjectAttribute
    0.57
    jib
    0.56
    UMNS
    0.55
    expandindo
    0.55
     '>=
    0.54
    </thead>
    0.53
    hoots
    0.52
    Activations Density 1.557%

    No Known Activations