© 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. 4-CLT-HP
    7. 2837
    Prev
    Next
    INDEX
    Explanations

    Research institutions & codes

    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
    CGRectMake
    -0.53
    ----</
    -0.52
     gü
    -0.49
    ลักษ
    -0.48
     etc
    -0.45
     ExecuteAsync
    -0.44
    inska
    -0.44
    نام
    -0.44
    APK
    -0.43
     cross
    -0.43
    POSITIVE LOGITS
     وتسجيلات
    0.59
     hôtes
    0.56
    הערות
    0.52
    Identyfik
    0.51
     Laboratories
    0.49
     médicaux
    0.49
     Mitochondrial
    0.48
    cyklopedia
    0.48
     useDispatch
    0.48
     NKC
    0.47
    Activations Density 0.014%

    No Known Activations