© 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. 38841
    Prev
    Next
    INDEX
    Explanations

    inviting

    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
     financières
    -0.63
    Centered
    -0.61
    pausal
    -0.57
     Breakers
    -0.57
     récupération
    -0.56
    Caesar
    -0.55
     dévelo
    -0.55
     vectorielle
    -0.55
     negativos
    -0.54
     referenties
    -0.53
    POSITIVE LOGITS
    ly
    0.82
    maßen
    0.66
    LY
    0.62
    jmniej
    0.61
    wiſe
    0.61
    ness
    0.60
    adays
    0.59
    ptonshire
    0.59
    lyse
    0.58
    protoimpl
    0.57
    Activations Density 0.069%

    No Known Activations