© 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. 41824
    Prev
    Next
    INDEX
    Explanations

    item

    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
     item
    -2.06
     Item
    -1.76
     items
    -1.63
    Item
    -1.59
     Items
    -1.51
    item
    -1.41
     ITEM
    -1.38
    Items
    -1.37
     ITEMS
    -1.35
    ITEM
    -1.20
    POSITIVE LOGITS
    ization
    0.98
    ize
    0.84
    ized
    0.73
    RenderAtEndOf
    0.68
    izing
    0.59
    isation
    0.57
    izations
    0.52
    imper
    0.50
    ign
    0.50
    irse
    0.49
    Activations Density 0.346%

    No Known Activations