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. 74311
    Prev
    Next
    INDEX
    Explanations

    Manny

    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
    ConstraintMaker
    -0.90
     Мексичка
    -0.68
     InputDecoration
    -0.66
    IntoConstraints
    -0.64
    Билгалдахарш
    -0.63
    AddTagHelper
    -0.63
     doInBackground
    -0.62
     hyal
    -0.57
     BoxDecoration
    -0.57
    DataRow
    -0.56
    POSITIVE LOGITS
     CP
    0.60
    matchCondition
    0.57
     Z
    0.57
     CURIAM
    0.52
     ApiException
    0.51
    #
    
    0.47
     OP
    0.46
     z
    0.44
    antian
    0.44
     Advanced
    0.44
    Activations Density 0.004%

    No Known Activations