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. 74252
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    jss
    -0.54
    rous
    -0.52
     sns
    -0.51
     GQ
    -0.50
     getItemCount
    -0.48
     Pli
    -0.47
    UpInside
    -0.47
     Marat
    -0.47
    SQLiteDatabase
    -0.47
     Trunk
    -0.47
    POSITIVE LOGITS
     المعيارى
    0.66
    igshid
    0.63
    цездатний
    0.57
     مشين
    0.57
    ⓧ
    0.56
     صوتيه
    0.56
     ujednoznacz
    0.54
    SBATCH
    0.54
    новништво
    0.53
    EDEFAULT
    0.52
    Activations Density 0.082%

    No Known Activations