© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1192
    Prev
    Next
    INDEX
    Explanations

    leuk

    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
     juda
    -0.52
     guaranteed
    -0.48
     country
    -0.48
     IDisposable
    -0.48
    ,
    -0.47
     TW
    -0.46
     twins
    -0.46
     basi
    -0.46
     commonwealth
    -0.46
     ancho
    -0.45
    POSITIVE LOGITS
    APORE
    0.73
    uxxxx
    0.63
     oreilles
    0.58
     fédé
    0.57
     INTERESAR
    0.57
    cèse
    0.56
    adpleegd
    0.54
     démocr
    0.54
    اریخ
    0.54
     ddelweddau
    0.54
    Activations Density 0.489%

    No Known Activations