© 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. 76476
    Prev
    Next
    INDEX
    Explanations

    code fragments

    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
    pela
    -0.48
     Rhein
    -0.44
     Mün
    -0.44
    hiri
    -0.43
     يلي
    -0.41
     conven
    -0.41
    haraan
    -0.40
    Itoa
    -0.40
    RAP
    -0.40
    ベント
    -0.39
    POSITIVE LOGITS
    +:+
    0.81
    stdc
    0.76
    WriteTagHelper
    0.74
     فريبيس
    0.68
    localctx
    0.66
     propOrder
    0.66
    Spoljašnje
    0.60
    NewUrlParser
    0.58
    InjectAttribute
    0.58
    Tikang
    0.58
    Activations Density 0.007%

    No Known Activations