© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95104
    Prev
    Next
    INDEX
    Explanations

    of

    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
    новништво
    -0.63
    archiviato
    -0.56
    onium
    -0.53
    fxml
    -0.53
    oteca
    -0.51
    netbeans
    -0.50
     convertView
    -0.50
     AttributeSet
    -0.50
    apolis
    -0.50
    thma
    -0.49
    POSITIVE LOGITS
     course
    0.79
     which
    0.75
    course
    0.63
     WHICH
    0.62
     whose
    0.62
     cuál
    0.60
     seeing
    0.59
    which
    0.57
     discussing
    0.56
     enjoying
    0.55
    Activations Density 0.002%

    No Known Activations