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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73972
    Prev
    Next
    INDEX
    Explanations

    Internet and software context

    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
     doInBackground
    -0.63
     '\\;'
    -0.63
    EndTag
    -0.56
     الرياضيه
    -0.56
    elemField
    -0.55
    matchCondition
    -0.54
    expandindo
    -0.53
    HostException
    -0.53
    cupa
    -0.52
     NUKAT
    -0.51
    POSITIVE LOGITS
     emp
    0.66
    };*/
    0.57
     dep
    0.56
     pan
    0.54
     falling
    0.51
     cutting
    0.48
     ha
    0.46
     spread
    0.46
    وبة
    0.46
    gezogen
    0.45
    Activations Density 0.003%

    No Known Activations