© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    bog

    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
     bog
    -0.70
     Италијани
    -0.69
     EconPapers
    -0.60
    قایناق‌لار
    -0.59
     InputDecoration
    -0.58
    AndEndTag
    -0.57
    يات
    -0.55
     Signalez
    -0.54
     Bog
    -0.52
     dou
    -0.51
    POSITIVE LOGITS
    __*/
    0.67
     obé
    0.61
    Gambas
    0.59
     تضيفلها
    0.57
    gings
    0.57
    drücken
    0.57
    AddWithValue
    0.54
    fillType
    0.52
    ged
    0.52
    GERS
    0.52
    Activations Density 1.234%

    No Known Activations