© 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. 98269
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    LookAnd
    -0.92
    tagHelperRunner
    -0.87
    webElementXpaths
    -0.86
    InjectAttribute
    -0.82
    ImageContext
    -0.82
    uxxxx
    -0.79
     ***!
    -0.79
    енча
    -0.78
    UserScript
    -0.75
    rungsseite
    -0.74
    POSITIVE LOGITS
     Theſe
    0.59
     Kün
    0.52
     Majefty
    0.52
    ;';
    0.48
     itſelf
    0.45
     Houſe
    0.45
     houſe
    0.44
    ſelf
    0.43
    \<^
    0.43
     Hift
    0.42
    Activations Density 0.004%

    No Known Activations