© 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. 0-CLT-HP
    7. 43921
    Prev
    Next
    INDEX
    Explanations

    term

    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
     term
    -2.78
    term
    -2.41
    Term
    -2.36
     Term
    -2.30
     terms
    -2.22
    terms
    -2.06
    Terms
    -1.91
     terme
    -1.91
     TERM
    -1.86
     Terms
    -1.84
    POSITIVE LOGITS
     resourceCulture
    0.71
     ویکی‌پدی
    0.64
     marito
    0.60
    Geplaatst
    0.60
     kaynağından
    0.59
     féminine
    0.57
     FontWeight
    0.56
     gatto
    0.56
    bootstrapcdn
    0.56
     ogóle
    0.55
    Activations Density 0.036%

    No Known Activations