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. 74457
    Prev
    Next
    INDEX
    Explanations

    Formal statements

    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
     Vikipedi
    -0.68
    saraba
    -0.63
    fjspx
    -0.61
    bootstrapcdn
    -0.59
    LoadScene
    -0.57
     Мексичка
    -0.56
     transfieras
    -0.56
    клопе
    -0.53
    TagMode
    -0.51
     resourceCulture
    -0.50
    POSITIVE LOGITS
     present
    0.73
     utter
    0.64
     coin
    0.63
     float
    0.62
     state
    0.61
     prosent
    0.61
    Distribuzione
    0.60
     voice
    0.59
     point
    0.57
     hazard
    0.57
    Activations Density 0.020%

    No Known Activations