© 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. 4-CLT-HP
    7. 3069
    Prev
    Next
    INDEX
    Explanations

    game

    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
    culated
    -0.47
     reduction
    -0.47
     expansion
    -0.47
     reduc
    -0.45
    testify
    -0.44
    슘
    -0.43
     dilution
    -0.42
     pairing
    -0.42
    Portály
    -0.42
    ArgsConstructor
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.71
    >);
    0.62
     ddelweddau
    0.58
     then
    0.56
     quelconque
    0.55
     THEN
    0.55
    RuleContext
    0.55
     colère
    0.54
     allora
    0.54
    💈
    0.54
    Activations Density 0.008%

    No Known Activations