© 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. 0-CLT-HP
    4. 97758
    Prev
    Next
    INDEX
    Explanations

    senators

    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
    e
    -0.66
    em
    -0.60
    a
    -0.59
     arena
    -0.59
    o
    -0.56
    ed
    -0.54
    Em
    -0.53
     Fra
    -0.52
    pushFollow
    -0.51
    AndroidJUnit
    -0.50
    POSITIVE LOGITS
     ainfi
    0.71
     gouvernements
    0.70
     avoient
    0.69
    rizona
    0.67
    Scopri
    0.67
    excellents
    0.66
     esprits
    0.65
     étoient
    0.63
     rigue
    0.63
     neutre
    0.63
    Activations Density 0.342%

    No Known Activations