© 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. 91661
    Prev
    Next
    INDEX
    Explanations

    @

    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
    StoryboardSegue
    -0.76
    findpost
    -0.68
    ImageContext
    -0.66
     InputDecoration
    -0.57
     BoxDecoration
    -0.56
    DoubleQuotes
    -0.55
    ","");
    -0.54
    мум
    -0.54
    +:+
    -0.54
    IntoConstraints
    -0.52
    POSITIVE LOGITS
    RegressionTest
    0.65
    subpackage
    0.60
    titleMargin
    0.56
    +#+#
    0.53
     clearfix
    0.48
    Démographie
    0.47
     beginnetje
    0.45
     boîtes
    0.45
    obenz
    0.44
    ท์
    0.43
    Activations Density 0.002%

    No Known Activations