© 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. 76806
    Prev
    Next
    INDEX
    Explanations

    Problems/incidents

    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
    MigrationBuilder
    -0.64
    ineno
    -0.59
    AndEndTag
    -0.58
    AnimationsModule
    -0.54
    encodeWith
    -0.54
    __)
    -0.54
    Datuak
    -0.52
    prefixer
    -0.48
     fija
    -0.48
     EnglishChoose
    -0.48
    POSITIVE LOGITS
     reft
    0.56
    ouille
    0.53
    참고
    0.49
     esternos
    0.49
     deposited
    0.48
    álogos
    0.48
     sent
    0.47
    icator
    0.46
    bels
    0.45
     secreted
    0.45
    Activations Density 0.001%

    No Known Activations