© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 962
    Prev
    Next
    INDEX
    Explanations

    describe

    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
    jois
    -0.57
    esez
    -0.54
    glTranslatef
    -0.51
    ainville
    -0.51
    RoutingModule
    -0.50
    StoreMessageInfo
    -0.50
    PageModule
    -0.50
     description
    -0.50
    fflush
    -0.49
    phée
    -0.49
    POSITIVE LOGITS
    Personensuche
    0.53
     bonté
    0.52
     lenker
    0.50
     about
    0.49
    MigrationBuilder
    0.47
    WithIdentifier
    0.46
     udaler
    0.45
    ToTensor
    0.45
     vieilles
    0.44
    ioutil
    0.44
    Activations Density 0.052%

    No Known Activations