© 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. 75142
    Prev
    Next
    INDEX
    Explanations

    technical terminology

    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
    parsedMessage
    -0.55
    DeleteBehavior
    -0.50
    ();)
    -0.47
     Roskov
    -0.47
     समीक्षक
    -0.43
     VIDEOTAPE
    -0.43
    GOTREF
    -0.41
    Наводи
    -0.41
    ❋
    -0.39
     protoimpl
    -0.38
    POSITIVE LOGITS
     Winaray
    0.71
    InitVars
    0.69
    XtraReports
    0.66
     Shakspeare
    0.62
     Clow
    0.61
    mortem
    0.61
    ortium
    0.61
     Italijani
    0.59
     Majefty
    0.59
    putan
    0.57
    Activations Density 0.001%

    No Known Activations