© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95147
    Prev
    Next
    INDEX
    Explanations

    care

    np_max-act · 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
    AccessorTable
    -0.78
     WebApplication
    -0.73
     فريبيس
    -0.69
    aarrggbb
    -0.68
    
    -0.67
    Hochspringen
    -0.66
    AndEndTag
    -0.66
    Carriera
    -0.65
     Offisielt
    -0.60
    GEBURTS
    -0.59
    POSITIVE LOGITS
    CardBody
    0.45
    šinou
    0.43
    IBarButtonItem
    0.42
    iree
    0.42
    CAPTION
    0.41
     MCT
    0.41
     pap
    0.41
     bfs
    0.41
    ofire
    0.41
     papers
    0.40
    Activations Density 0.001%

    No Known Activations