© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43718
    Prev
    Next
    INDEX
    Explanations

    college/university

    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
    .
    -0.56
    -
    -0.52
    ,
    -0.50
    ;
    -0.45
    ↵↵
    -0.44
     in
    -0.44
     A
    -0.43
     to
    -0.42
     (
    -0.42
    A
    -0.42
    POSITIVE LOGITS
    parsedMessage
    1.51
    Personendaten
    1.29
    SourceChecksum
    1.27
    aarrggbb
    1.25
    PreferredItem
    1.23
    tagHelperRunner
    1.23
     myſelf
    1.22
    Билгалдахарш
    1.19
     Efq
    1.19
    脚注の使い方
    1.18
    Activations Density 0.367%

    No Known Activations