© 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. 5-CLT-HP
    7. 53
    Prev
    Next
    INDEX
    Explanations

    Comparison

    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
    Aiheesta
    -0.62
    <bos>
    -0.61
    enterOuterAlt
    -0.56
    Lähteet
    -0.56
     resourceCulture
    -0.56
    ">//
    -0.55
    agrama
    -0.51
    ädie
    -0.48
    windowFixed
    -0.47
    tyd
    -0.47
    POSITIVE LOGITS
    Throwaway
    0.55
    tagHelperRunner
    0.55
     or
    0.54
    étit
    0.54
    ing
    0.52
    lorn
    0.51
    ēj
    0.51
    ThroughAttribute
    0.50
     <<<<<<<<<<<<<<
    0.48
     then
    0.47
    Activations Density 0.033%

    No Known Activations