© 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. 1-CLT-HP
    7. 12411
    Prev
    Next
    INDEX
    Explanations

    ionized

    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
     ionized
    -0.54
     vostri
    -0.52
     Um
    -0.47
     Micro
    -0.47
     U
    -0.44
     slik
    -0.43
     bouche
    -0.42
     Old
    -0.41
     micro
    -0.40
     G
    -0.40
    POSITIVE LOGITS
     Roskov
    0.77
     auffi
    0.75
    IsMutable
    0.75
    談社
    0.72
    脚注の使い方
    0.67
     GoogleFonts
    0.67
    يميديا
    0.66
    (!__
    0.65
     preſent
    0.64
    RectangleBorder
    0.64
    Activations Density 0.259%

    No Known Activations