© 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. 1-CLT-HP
    7. 8654
    Prev
    Next
    INDEX
    Explanations

    ammonia

    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
    IntoConstraints
    -0.75
    ConstraintMaker
    -0.61
    aarrggbb
    -0.55
     ammonia
    -0.50
     nakalista
    -0.46
    CodeAttribute
    -0.44
    IsContent
    -0.43
    BeginInit
    -0.43
     Administrativna
    -0.42
     Autorisations
    -0.42
    POSITIVE LOGITS
    ГЛА
    0.63
    égias
    0.59
    VersionUID
    0.57
    testify
    0.56
     cardiaque
    0.56
    findpost
    0.56
     mukana
    0.56
    argout
    0.55
     réaliste
    0.54
     déco
    0.54
    Activations Density 0.017%

    No Known Activations