© 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. 4-CLT-HP
    7. 651
    Prev
    Next
    INDEX
    Explanations

    one

    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
    ulescu
    -0.59
     незавершена
    -0.56
     utafitiHapana
    -0.56
     LUMP
    -0.53
     kaynağından
    -0.51
     inhoud
    -0.50
    <!--[
    -0.50
    yelitis
    -0.50
     siapa
    -0.49
    цездатний
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.59
     chi̍t
    0.59
     decades
    0.57
     years
    0.56
     centuries
    0.52
     weeks
    0.51
    StreetMap
    0.50
     of
    0.48
    years
    0.48
     type
    0.47
    Activations Density 0.002%

    No Known Activations