© 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. 2565
    Prev
    Next
    INDEX
    Explanations

    Image credits and code

    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
     domestic
    -0.50
     dog
    -0.47
    acy
    -0.47
    ntry
    -0.47
     Frat
    -0.46
     attendance
    -0.46
     Dogs
    -0.46
     drag
    -0.45
     eye
    -0.45
    Runtime
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.82
    featureID
    0.71
     ostavi
    0.63
    rungsseite
    0.62
    :✨
    0.61
    InitVars
    0.60
    parsedMessage
    0.59
     onCancelled
    0.58
    دانشنامهٔ
    0.54
     igång
    0.54
    Activations Density 0.003%

    No Known Activations