© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92000
    Prev
    Next
    INDEX
    Explanations

    handle

    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
    expandindo
    -0.63
    RTLR
    -0.62
     оригіналу
    -0.61
     estekak
    -0.60
    parsedMessage
    -0.58
    WebControls
    -0.58
    raits
    -0.58
    imai
    -0.57
     EnglishChoose
    -0.57
    handleRequest
    -0.57
    POSITIVE LOGITS
    >//
    0.44
    CompilerServices
    0.41
     rhestr
    0.40
    nloa
    0.40
    ónde
    0.40
    ageo
    0.39
    lang
    0.38
    帖最后由
    0.38
    Redis
    0.38
    Generic
    0.37
    Activations Density 0.004%

    No Known Activations