© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3631
    Prev
    Next
    INDEX
    Explanations

    to

    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
    VersionUID
    -0.59
     näky
    -0.59
     prisonniers
    -0.58
    TagMode
    -0.56
    ργασ
    -0.55
     legado
    -0.54
     للاسماء
    -0.54
     handlar
    -0.54
    ateľ
    -0.54
     nuits
    -0.53
    POSITIVE LOGITS
     developing
    0.86
    UnusedPrivate
    0.73
     develop
    0.69
     producing
    0.66
     forming
    0.65
    developing
    0.61
     contracting
    0.60
     Developing
    0.57
    Developing
    0.57
    contentLoaded
    0.56
    Activations Density 0.005%

    No Known Activations