© 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. 20-CLT-HP
    7. 72455
    Prev
    Next
    INDEX
    Explanations

    code and metadata

    np_max-act-logits · 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
     препратки
    -0.73
    ientôt
    -0.71
    Spoljašnje
    -0.70
    IsMutable
    -0.66
     gainera
    -0.66
    UrlResolution
    -0.65
    Obrázky
    -0.65
    UnusedPrivate
    -0.64
     propOrder
    -0.64
    oosevelt
    -0.63
    POSITIVE LOGITS
     виправивши
    0.57
     Tinker
    0.52
    tik
    0.47
     Gine
    0.46
     TRAB
    0.46
     Hecho
    0.45
     ras
    0.45
     stik
    0.45
     prefixed
    0.45
    lo
    0.44
    Activations Density 0.003%

    No Known Activations