© 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. 1949
    Prev
    Next
    INDEX
    Explanations

    work

    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
     works
    -0.64
    poses
    -0.58
    ndham
    -0.56
     Barrow
    -0.54
    HTTPResponse
    -0.50
     work
    -0.50
     targets
    -0.50
    captures
    -0.49
    __()
    -0.48
    forName
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     done
    0.76
     Roskov
    0.75
    tagHelperRunner
    0.69
    oredCriteria
    0.68
    tanleria
    0.65
    WebVitals
    0.64
     performed
    0.61
    Personendaten
    0.59
     Done
    0.58
    Activations Density 0.003%

    No Known Activations