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. 74197
    Prev
    Next
    INDEX
    Explanations

    col

    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
    principalColumn
    -0.59
    +#+#
    -0.56
    
    -0.52
    migrationBuilder
    -0.49
    glGet
    -0.49
     Struct
    -0.44
     Rib
    -0.44
     repulsion
    -0.44
     Tamb
    -0.43
     بیر
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.98
    AddWithValue
    0.63
    WithMany
    0.55
     EconPapers
    0.54
    modore
    0.49
    farin
    0.48
    DropColumn
    0.47
    Aholisi
    0.47
     useParams
    0.47
    SharedDtor
    0.46
    Activations Density 0.002%

    No Known Activations