© 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. 2140
    Prev
    Next
    INDEX
    Explanations

    each

    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
     >=",
    -0.66
    цездатний
    -0.66
    :✨
    -0.66
    featureID
    -0.65
    zzleHttp
    -0.62
     تضيفلها
    -0.62
     cherchés
    -0.61
    ItemBackground
    -0.57
     resté
    -0.57
     roulant
    -0.57
    POSITIVE LOGITS
    others
    1.86
     other
    1.79
     others
    1.68
    other
    1.55
     Other
    1.34
     Others
    1.34
    Other
    1.33
     otros
    1.32
    Others
    1.31
     OTHERS
    1.26
    Activations Density 0.005%

    No Known Activations