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. 74419
    Prev
    Next
    INDEX
    Explanations

    Other languages

    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
    SourceChecksum
    -0.74
    GOTREF
    -0.71
    picks
    -0.71
    ModelBuilder
    -0.69
    клопе
    -0.68
     Picks
    -0.67
    setVerticalGroup
    -0.67
    protoimpl
    -0.67
    VideoCapture
    -0.66
    djangoproject
    -0.65
    POSITIVE LOGITS
     pitié
    0.44
     religieuses
    0.43
     religiosas
    0.42
     chré
    0.39
     dientes
    0.38
     définiti
    0.37
     religiosos
    0.36
     diritti
    0.35
     længere
    0.35
     større
    0.34
    Activations Density 0.005%

    No Known Activations