© 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. 5-CLT-HP
    7. 5392
    Prev
    Next
    INDEX
    Explanations

    about

    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
     Ombudsman
    -0.50
     VIDEOTAPE
    -0.49
     flesta
    -0.49
    iché
    -0.48
     ouvertes
    -0.47
    UnknownFields
    -0.46
    Sinopsis
    -0.45
     correctes
    -0.45
     intégr
    -0.44
    idey
    -0.43
    POSITIVE LOGITS
    contentLoaded
    0.71
    esModule
    0.62
     our
    0.60
     transfieras
    0.60
     ways
    0.59
    greenrobot
    0.59
    principalTable
    0.59
    MigrationBuilder
    0.57
    /******/
    0.56
    ніципалі
    0.55
    Activations Density 0.001%

    No Known Activations