© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45633
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     Roskov
    -0.57
     defStyle
    -0.53
     Trends
    -0.51
    alism
    -0.51
    epam
    -0.50
     Trend
    -0.49
     numberOfRows
    -0.49
    illère
    -0.48
     NSCoder
    -0.48
    kable
    -0.48
    POSITIVE LOGITS
     screen
    0.52
    argout
    0.52
    ccione
    0.52
     Vitamina
    0.50
    <bos>
    0.49
    Referencie
    0.49
     présidentielle
    0.48
    RTLD
    0.48
    렷
    0.48
    SerializeField
    0.47
    Activations Density 0.109%

    No Known Activations