© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75243
    Prev
    Next
    INDEX
    Explanations

    coding questions/language

    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
     للاسماء
    -0.79
    kháu
    -0.71
    Obrázky
    -0.70
     gynhyrchwyd
    -0.69
    rungsseite
    -0.69
    findpost
    -0.68
     linkovi
    -0.65
     समीक्षाओं
    -0.63
     AssemblyTitle
    -0.63
    providedIn
    -0.63
    POSITIVE LOGITS
     low
    0.48
     zero
    0.42
     human
    0.42
     Low
    0.40
    owol
    0.39
     zo
    0.38
     menschlichen
    0.36
     vitt
    0.36
    PRWEB
    0.36
     CWE
    0.36
    Activations Density 0.000%

    No Known Activations