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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2361
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     which
    -0.77
     with
    -0.68
     including
    -0.64
     as
    -0.60
     like
    -0.49
     or
    -0.48
     especially
    -0.48
    ↵↵
    -0.48
     without
    -0.47
     though
    -0.46
    POSITIVE LOGITS
     …)
    0.74
    RenderAtEndOf
    0.72
    ########.
    0.70
     OFDb
    0.70
    Personensuche
    0.69
    windowFixed
    0.68
     utafitiHapana
    0.68
    …).
    0.68
    …)
    0.67
     ...)
    0.67
    Activations Density 0.000%

    No Known Activations