© 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. 20-CLT-HP
    7. 74562
    Prev
    Next
    INDEX
    Explanations

    Code/data snippets

    np_max-act-logits · 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
     متعلقه
    -0.61
    voorbeeld
    -0.54
     Sext
    -0.49
    Tikang
    -0.49
     insuffisamment
    -0.49
     kysy
    -0.47
     مرئيه
    -0.47
     PyObject
    -0.46
     Dif
    -0.45
    ритори
    -0.44
    POSITIVE LOGITS
     Meksiku
    0.60
    AutoField
    0.54
    BeginContext
    0.53
    inaison
    0.53
    rapment
    0.52
    "]));
    0.50
     rekla
    0.50
    ueba
    0.49
    ListTile
    0.49
    })`
    0.49
    Activations Density 0.002%

    No Known Activations