© 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. 969
    Prev
    Next
    INDEX
    Explanations

    under

    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
    \{\\
    -0.81
    any
    -0.57
    PerformLayout
    -0.54
    cent
    -0.53
    ys
    -0.53
    })();
    -0.47
    })()
    -0.47
     vorn
    -0.47
     afect
    -0.45
    rég
    -0.45
    POSITIVE LOGITS
    PreAuthorize
    0.80
    kháu
    0.68
    raszam
    0.68
     Мексичка
    0.67
     الرخصة
    0.66
    DataAnnotations
    0.63
    aspectj
    0.63
     BorderRadius
    0.61
    jectures
    0.60
     CGSize
    0.59
    Activations Density 0.003%

    No Known Activations