© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93173
    Prev
    Next
    INDEX
    Explanations

    Snippets of extracted text

    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
    ToScroll
    -0.64
     समीक्षाओं
    -0.61
    ed
    -0.58
    ling
    -0.57
    انجليز
    -0.56
    writerow
    -0.56
    帖最后由
    -0.55
    Vors
    -0.54
     banding
    -0.53
     Aviation
    -0.52
    POSITIVE LOGITS
    UnsafeEnabled
    0.53
    enerbahçe
    0.50
    basicConfig
    0.49
    nesia
    0.49
     berupa
    0.47
    Disposed
    0.47
     саны
    0.47
    renia
    0.46
    beforeAll
    0.46
    propane
    0.46
    Activations Density 0.144%

    No Known Activations