© 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. 20-CLT-HP
    7. 76665
    Prev
    Next
    INDEX
    Explanations

    Code snippets/documentation

    np_max-act-logits · 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
    Przypisy
    -0.49
     field
    -0.46
     teren
    -0.46
    endmodule
    -0.46
    anskje
    -0.44
    siąż
    -0.44
     Kiel
    -0.44
    ISupport
    -0.44
     census
    -0.43
     Felic
    -0.43
    POSITIVE LOGITS
     proposons
    0.69
    fördert
    0.59
    ölkerung
    0.59
     AssemblyCulture
    0.59
     propOrder
    0.59
     gainera
    0.59
     volna
    0.58
    tagext
    0.56
    NewUrlParser
    0.56
    riwal
    0.56
    Activations Density 0.001%

    No Known Activations