© 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. 9588
    Prev
    Next
    INDEX
    Explanations

    data

    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
     GenerationType
    -0.74
    BeginContext
    -0.72
    EDEFAULT
    -0.64
    }();
    -0.64
     NSCoder
    -0.63
     FetchType
    -0.63
     الحره
    -0.62
     trajets
    -0.62
     createContext
    -0.62
    '},
    -0.61
    POSITIVE LOGITS
    Sper
    0.47
    хьтан
    0.45
     Sper
    0.44
    ője
    0.44
     Ejec
    0.44
    orgon
    0.44
    ői
    0.43
     Haf
    0.41
    ViewFeatures
    0.41
    Spoljašnje
    0.41
    Activations Density 0.013%

    No Known Activations