© 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. 261
    Prev
    Next
    INDEX
    Explanations

    formal writing

    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
    Personendaten
    -0.68
     surla
    -0.60
    NewUrlParser
    -0.57
    Véxase
    -0.56
    VersionUID
    -0.55
    ագրություններ
    -0.53
     proprement
    -0.52
     arşivlendi
    -0.52
    новниш
    -0.52
     himſelf
    -0.49
    POSITIVE LOGITS
     clues
    0.60
    клопе
    0.54
    ROC
    0.52
     cues
    0.51
     hints
    0.48
    tonode
    0.47
     top
    0.47
     insights
    0.47
    циа
    0.47
     advice
    0.46
    Activations Density 0.004%

    No Known Activations