© 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. 91598
    Prev
    Next
    INDEX
    Explanations

    store

    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
    Portale
    -0.56
    ########.
    -0.54
    rieben
    -0.54
     informée
    -0.50
    Portály
    -0.50
     Bogen
    -0.50
    ticism
    -0.48
     Weil
    -0.48
    WEBPACK
    -0.46
     Stubbs
    -0.45
    POSITIVE LOGITS
    front
    0.75
    MigrationBuilder
    0.75
    window
    0.69
     front
    0.69
     merchandising
    0.66
     window
    0.66
     shopping
    0.65
     butik
    0.63
    ReusableCell
    0.63
    :✨
    0.61
    Activations Density 0.002%

    No Known Activations