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. 20-CLT-HP
    4. 74111
    Prev
    Next
    INDEX
    Explanations

    Various contexts

    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
     للاسماء
    -0.65
    ThroughAttribute
    -0.64
     surla
    -0.60
     שוליים
    -0.58
     mergeFrom
    -0.53
    ksikon
    -0.52
    rzost
    -0.52
    consulté
    -0.52
    躇
    -0.51
    ământ
    -0.49
    POSITIVE LOGITS
    VideoCapture
    0.71
     backs
    0.56
     lay
    0.55
     IBOutlet
    0.54
    backs
    0.54
     utafitiHapana
    0.54
     Lay
    0.51
     Unsplash
    0.51
     digress
    0.51
     لهم
    0.50
    Activations Density 0.000%

    No Known Activations