© 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. 0-CLT-HP
    7. 38902
    Prev
    Next
    INDEX
    Explanations

    SE

    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
    SE
    -1.30
     SE
    -0.77
    MF
    -0.66
     sanitarias
    -0.59
     culturelles
    -0.56
     singolo
    -0.54
    posição
    -0.54
     diarias
    -0.53
     lisse
    -0.53
     dépos
    -0.52
    POSITIVE LOGITS
    enumi
    0.61
    AlterField
    0.61
    XmlAccessType
    0.60
    Ecotoxicity
    0.59
    
    0.58
     Administrativna
    0.57
     typelib
    0.57
    >`;
    0.55
    Портали
    0.54
    FRANCE
    0.54
    Activations Density 0.292%

    No Known Activations