© 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. 5-CLT-HP
    7. 92658
    Prev
    Next
    INDEX
    Explanations

    vacuum

    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
    !("{}",
    -0.59
    HtmlAttribute
    -0.54
     bezeichneter
    -0.53
    NOPQRST
    -0.53
    வர்
    -0.52
    rawDesc
    -0.52
    NamedQueries
    -0.51
     esterni
    -0.49
    obes
    -0.49
    PHONY
    -0.49
    POSITIVE LOGITS
     AspNetCore
    0.59
    PreExecute
    0.56
    source
    0.54
    DockStyle
    0.52
    ContentAsync
    0.52
    esModule
    0.50
     potenciales
    0.48
     paie
    0.47
     ExecuteAsync
    0.47
     médicaux
    0.47
    Activations Density 0.001%

    No Known Activations