© 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. 1-CLT-HP
    7. 13991
    Prev
    Next
    INDEX
    Explanations

    a

    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
    bbene
    -0.65
    romolecules
    -0.61
    suff
    -0.56
    ikasi
    -0.53
    rishnan
    -0.52
    ichord
    -0.50
     skjø
    -0.50
    ethene
    -0.50
    처럼
    -0.50
    atshirt
    -0.49
    POSITIVE LOGITS
     bunch
    0.75
    lot
    0.71
     LOT
    0.68
     lot
    0.68
    MLLoader
    0.67
     ton
    0.66
     lotta
    0.66
     host
    0.66
    LookAnd
    0.65
     TON
    0.63
    Activations Density 0.059%

    No Known Activations