Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74272
    Prev
    Next
    INDEX
    Explanations

    inhibition

    np_max-act-logits · 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
    ander
    -0.52
    Carcinogenicity
    -0.48
    forRoot
    -0.47
    ciller
    -0.46
    meral
    -0.46
    iesto
    -0.46
     meub
    -0.45
    amethasone
    -0.45
    enetrable
    -0.45
    胞
    -0.45
    POSITIVE LOGITS
     оригіналу
    0.70
     NSCoder
    0.61
    存于互联网档案馆
    0.57
     Dernière
    0.57
    typeorm
    0.57
    StructEnd
    0.56
    Tikang
    0.55
     Lillie
    0.55
    RetentionPolicy
    0.54
     Walkover
    0.53
    Activations Density 0.002%

    No Known Activations