© 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. 92078
    Prev
    Next
    INDEX
    Explanations

    online forum/blog excerpts

    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
    ^(@)
    -0.73
    erapeu
    -0.71
     fate
    -0.67
     cultures
    -0.64
     re
    -0.60
     surgeons
    -0.58
     manufactures
    -0.58
     hold
    -0.57
     concessions
    -0.57
     bloggers
    -0.57
    POSITIVE LOGITS
    contentLoaded
    0.61
    findpost
    0.59
    Datuak
    0.54
    </thead>
    0.53
     fieldNum
    0.53
    ViewInit
    0.51
    the
    0.50
    sum
    0.50
    top
    0.50
     فريبيس
    0.49
    Activations Density 1.021%

    No Known Activations