© 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. 20-CLT-HP
    7. 76354
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical research

    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
     influence
    -1.77
    Influence
    -1.75
     impact
    -1.73
    Impact
    -1.73
    influence
    -1.70
     Influence
    -1.69
    impact
    -1.65
     Impact
    -1.64
     impacts
    -1.60
     Impacts
    -1.54
    POSITIVE LOGITS
    OGND
    0.52
    abetes
    0.38
    bd
    0.37
    MigrationBuilder
    0.36
    кас
    0.35
    фин
    0.33
    发表于
    0.32
     Borg
    0.32
     Weltkrieg
    0.32
     Πε
    0.31
    Activations Density 0.001%

    No Known Activations