© 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. 97759
    Prev
    Next
    INDEX
    Explanations

    Code/Legal documents

    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
    Autoritní
    -0.73
     виправивши
    -0.63
    Enllaces
    -0.59
     acrob
    -0.57
    uary
    -0.55
    yto
    -0.54
     kasarigan
    -0.53
    KeySpec
    -0.52
    Portail
    -0.52
     autorytatywna
    -0.52
    POSITIVE LOGITS
    atic
    0.71
    ats
    0.62
    ranean
    0.55
    acne
    0.51
    áticas
    0.49
    ática
    0.49
    ATIC
    0.49
    áticos
    0.47
    noopener
    0.47
     saites
    0.47
    Activations Density 2.151%

    No Known Activations