Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 343
    Prev
    Next
    INDEX
    Explanations

    legal cases

    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
    ema
    -0.66
    ed
    -0.65
    e
    -0.63
    eer
    -0.60
    eves
    -0.59
    eme
    -0.58
    ("]");
    -0.58
    brough
    -0.57
    "}";
    -0.56
    thaler
    -0.54
    POSITIVE LOGITS
     mourut
    0.57
    NUMX
    0.51
    Pty
    0.48
     requestCode
    0.47
     Arsen
    0.47
    siapkan
    0.47
     postIndex
    0.47
     livraison
    0.46
    ostante
    0.46
     ASC
    0.44
    Activations Density 0.116%

    No Known Activations