© 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. 1-CLT-HP
    7. 9629
    Prev
    Next
    INDEX
    Explanations

    in

    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
    transQ
    -0.54
    vimeo
    -0.50
    urier
    -0.49
     Meksiku
    -0.47
    StreetMap
    -0.46
    RectangleBorder
    -0.45
    ahalli
    -0.45
     ModelExpression
    -0.44
    addPreferredGap
    -0.44
     يتيمه
    -0.44
    POSITIVE LOGITS
     particular
    0.86
    particular
    0.85
     sight
    0.84
     WebDriverWait
    0.70
     PARTICULAR
    0.69
     NSCoder
    0.69
     Particular
    0.69
     Theſe
    0.67
     particolare
    0.64
    Particular
    0.63
    Activations Density 0.036%

    No Known Activations