© 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. 0-CLT-HP
    7. 94252
    Prev
    Next
    INDEX
    Explanations

    Chambers

    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
     Chambers
    -1.14
    Chambers
    -1.05
    TagMode
    -0.85
     Theſe
    -0.79
    ſelves
    -0.75
    ſelf
    -0.75
    rages
    -0.73
     Efq
    -0.73
    IsContent
    -0.73
     ་་
    -0.69
    POSITIVE LOGITS
    .
    0.63
    ,
    0.56
    abestanden
    0.52
    startActivity
    0.49
    calipsis
    0.47
    cèse
    0.47
     llevado
    0.46
    igslist
    0.46
    parsedMessage
    0.44
     led
    0.43
    Activations Density 1.769%

    No Known Activations