© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93795
    Prev
    Next
    INDEX
    Explanations

    more

    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
    MigrationBuilder
    -0.79
    دانشنامهٔ
    -0.68
     فريبيس
    -0.67
    :✨
    -0.66
     оригіналу
    -0.64
     Empieza
    -0.63
    AnimationsModule
    -0.63
    ThroughAttribute
    -0.63
    photobucket
    -0.61
    ]")]
    -0.61
    POSITIVE LOGITS
    onaceous
    0.57
     important
    0.50
     rarely
    0.48
    HttpPut
    0.48
     precisely
    0.47
    ')";
    0.46
    ಾಗಿ
    0.45
    __':
    0.44
    umenta
    0.44
    ')"
    0.42
    Activations Density 0.003%

    No Known Activations