© 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. 1-CLT-HP
    7. 15005
    Prev
    Next
    INDEX
    Explanations

    speech and language

    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
    mybatisplus
    -0.92
     disambiguazione
    -0.92
     himo
    -0.87
    цездатний
    -0.82
     typelib
    -0.81
    +:+
    -0.81
     pleaſure
    -0.79
    providedIn
    -0.79
    MigrationBuilder
    -0.76
    IsMutable
    -0.75
    POSITIVE LOGITS
    ,
    0.50
     of
    0.49
     and
    0.48
     E
    0.46
     Bour
    0.43
     R
    0.41
     T
    0.40
     or
    0.40
     opening
    0.39
     (
    0.39
    Activations Density 0.011%

    No Known Activations