© 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. 5-CLT-HP
    7. 2239
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     EconPapers
    -0.79
     كومونز
    -0.71
    mybatisplus
    -0.68
    tableFuture
    -0.68
    DatabaseError
    -0.65
    HostException
    -0.65
    ControllerAdvice
    -0.65
     الحره
    -0.64
    IsContent
    -0.64
    esterol
    -0.64
    POSITIVE LOGITS
    ništvo
    0.42
     linkovi
    0.41
    wnież
    0.40
     gena
    0.40
     μαύ
    0.36
    GETHER
    0.36
     vermelhas
    0.35
    شوند
    0.35
    maksud
    0.35
     negras
    0.35
    Activations Density 0.021%

    No Known Activations