© 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. 38822
    Prev
    Next
    INDEX
    Explanations

    cozy

    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
    aliana
    -0.71
    ye
    -0.69
    eye
    -0.69
     Wester
    -0.58
    nite
    -0.56
     estimés
    -0.56
    oye
    -0.56
    fine
    -0.55
    sweat
    -0.54
    Rüyada
    -0.51
    POSITIVE LOGITS
     transférez
    0.63
     OnInit
    0.52
     politiche
    0.51
     propOrder
    0.50
    انيف
    0.49
    شهاد
    0.48
    EndGlobalSection
    0.47
     tộc
    0.46
     normalidad
    0.46
    فایل‌لار
    0.46
    Activations Density 0.238%

    No Known Activations