© 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. 0-CLT-HP
    7. 95096
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical publications

    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
    ested
    -0.85
     Mende
    -0.64
    DateField
    -0.58
    esting
    -0.52
    ViewFeatures
    -0.50
     Konstantin
    -0.49
    IBOutlet
    -0.48
    os
    -0.48
     Tasman
    -0.47
     Ber
    -0.47
    POSITIVE LOGITS
     насељу
    0.68
    );?>
    0.65
    IndentedString
    0.65
    WarningLevel
    0.62
    Datuak
    0.60
    localctx
    0.60
     ITA
    0.60
    MigrationBuilder
    0.60
     censiti
    0.59
     SUDOC
    0.58
    Activations Density 0.027%

    No Known Activations