© 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. 20-CLT-HP
    7. 75903
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act-logits · 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
    脚注の使い方
    -0.43
    Candidate
    -0.43
    detta
    -0.43
     oprot
    -0.43
     Picking
    -0.43
    etcode
    -0.42
     acetic
    -0.42
    pushFollow
    -0.41
    ünkü
    -0.41
    Depart
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.85
    migrationBuilder
    0.75
     Baillargeon
    0.63
    /**
    0.61
    UnknownFieldSet
    0.61
    principalColumn
    0.56
    ])));
    0.56
     فريبيس
    0.55
     Seeder
    0.54
     Վերցված
    0.54
    Activations Density 0.002%

    No Known Activations