© 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. 12981
    Prev
    Next
    INDEX
    Explanations

    ocry

    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
     juveniles
    -0.76
    IsContent
    -0.70
     ModelExpression
    -0.64
    RegressionTest
    -0.59
     Réponses
    -0.58
     kasarigan
    -0.57
    
    -0.56
     Winaray
    -0.56
     calldata
    -0.55
     defaultstate
    -0.55
    POSITIVE LOGITS
    SuccessListener
    0.51
    same
    0.50
     vectorielles
    0.46
    Будь
    0.46
    nitive
    0.46
     mêmes
    0.44
    ///</
    0.44
     pouvoirs
    0.44
    ட்ச
    0.44
     miễn
    0.44
    Activations Density 0.053%

    No Known Activations