© 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. 92150
    Prev
    Next
    INDEX
    Explanations

    AN

    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
    ater
    -0.70
    navigation
    -0.62
    erman
    -0.62
    aten
    -0.60
    ghan
    -0.60
    CTIONS
    -0.55
    isms
    -0.54
    ered
    -0.53
    ctions
    -0.52
    ism
    -0.51
    POSITIVE LOGITS
    verwijspagina
    0.93
    $_['
    0.89
     utafitiHapana
    0.80
     Wikispecies
    0.72
     فريبيس
    0.71
    يميديا
    0.68
    Amicalement
    0.68
    VIAF
    0.67
    Externé
    0.67
     nahilalakip
    0.66
    Activations Density 1.598%

    No Known Activations