© 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. 15771
    Prev
    Next
    INDEX
    Explanations

    prove

    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
     proves
    -0.85
     prove
    -0.81
     proved
    -0.80
     proving
    -0.80
     intptr
    -0.76
    proven
    -0.73
    HtmlAttribute
    -0.73
     proven
    -0.71
    proved
    -0.69
    ImageContext
    -0.68
    POSITIVE LOGITS
    Démographie
    0.54
     palsu
    0.48
    ianum
    0.45
    usammen
    0.44
     виправивши
    0.43
    óż
    0.43
    敛
    0.42
     sánh
    0.42
    cera
    0.41
    bibfield
    0.41
    Activations Density 0.032%

    No Known Activations