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. 1-CLT-HP
    4. 11040
    Prev
    Next
    INDEX
    Explanations

    causality

    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
     myſelf
    -0.81
     purpoſe
    -0.80
    edo
    -0.76
     whoſe
    -0.76
     ContentValues
    -0.73
     autorytatywna
    -0.73
     дописавши
    -0.72
     ſeveral
    -0.71
     themſelves
    -0.70
     itſelf
    -0.69
    POSITIVE LOGITS
    uate
    0.47
    inians
    0.47
    喱
    0.46
    uis
    0.45
    agerie
    0.44
    ък
    0.43
    Iné
    0.43
    rester
    0.42
     Bir
    0.42
    sert
    0.41
    Activations Density 0.075%

    No Known Activations