© 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. 1-CLT-HP
    4. 45985
    Prev
    Next
    INDEX
    Explanations

    brandt

    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
    ensement
    -0.58
     âgées
    -0.58
    valuation
    -0.57
    raisal
    -0.57
    valuations
    -0.56
     समीक्षक
    -0.55
     travaillons
    -0.54
     laiss
    -0.54
     tabulation
    -0.54
    versary
    -0.53
    POSITIVE LOGITS
    toch
    0.63
    orsch
    0.60
    Diweddarwch
    0.57
     ket
    0.57
    Commands
    0.55
    springframework
    0.54
     frames
    0.53
     Kain
    0.52
    abstractmethod
    0.51
     command
    0.51
    Activations Density 0.011%

    No Known Activations