© 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. 1-CLT-HP
    7. 45629
    Prev
    Next
    INDEX
    Explanations

    body care

    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
    ValueStyle
    -0.66
     utafitiHapana
    -0.65
     estimés
    -0.58
    GraphicsUnit
    -0.56
     NSCoder
    -0.54
     transfieras
    -0.50
     numberOfRows
    -0.50
     kasarigan
    -0.48
     retraite
    -0.47
     समीक्षक
    -0.47
    POSITIVE LOGITS
    biz
    0.56
    loom
    0.56
    
    0.56
    ็จ
    0.56
    ",&
    0.55
    ,‎
    0.55
    viewport
    0.53
    GOTREF
    0.53
    yaz
    0.53
    neau
    0.52
    Activations Density 0.020%

    No Known Activations