© 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. 0-CLT-HP
    7. 43303
    Prev
    Next
    INDEX
    Explanations

    purport

    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
    agaimana
    -0.59
     Shakspeare
    -0.59
     &___
    -0.59
     Affiliation
    -0.59
    Espèce
    -0.59
     Schubert
    -0.58
     Shaksp
    -0.58
    spo
    -0.56
     Gera
    -0.56
    ships
    -0.56
    POSITIVE LOGITS
    enumi
    0.57
     مرئيه
    0.56
    enumii
    0.49
     خارجية
    0.47
     препратки
    0.47
    annu
    0.46
     للمعارف
    0.46
    Externí
    0.45
     cat
    0.45
    Odkazy
    0.45
    Activations Density 0.061%

    No Known Activations