© 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. 1-CLT-HP
    7. 9309
    Prev
    Next
    INDEX
    Explanations

    cible

    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
    cible
    -0.76
    cibility
    -0.69
    booth
    -0.61
     booth
    -0.58
    Booth
    -0.55
     Booth
    -0.54
     AssemblyTitle
    -0.49
    acke
    -0.48
    multicolumn
    -0.47
    CastException
    -0.46
    POSITIVE LOGITS
    ніципалі
    0.82
    jspx
    0.68
     CURIAM
    0.65
    urals
    0.65
    complexContent
    0.64
    SharedDtor
    0.63
     dianteiro
    0.60
     odkazy
    0.60
     StatelessWidget
    0.60
    StoryboardSegue
    0.60
    Activations Density 0.008%

    No Known Activations