© 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. 5-CLT-HP
    7. 95248
    Prev
    Next
    INDEX
    Explanations

    technical 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
     disambiguazione
    -0.90
    
    -0.85
    цездатний
    -0.83
     Pingback
    -0.81
    новниш
    -0.79
     InputDecoration
    -0.77
    ⓧ
    -0.77
    ंदीखरीदारी
    -0.77
    athread
    -0.73
    CloseOperation
    -0.71
    POSITIVE LOGITS
    .
    0.83
    ,
    0.60
    ;
    0.56
    Xna
    0.46
     –
    0.42
    --
    0.42
    aj
    0.42
     because
    0.42
     than
    0.41
     since
    0.41
    Activations Density 0.023%

    No Known Activations