© 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. 4609
    Prev
    Next
    INDEX
    Explanations

    code and computing

    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
    dehydes
    -0.51
     rituals
    -0.50
     ritual
    -0.49
    ็จ
    -0.48
     viewers
    -0.48
    طلحات
    -0.47
     tachy
    -0.47
     workmen
    -0.47
    criminator
    -0.47
     rites
    -0.46
    POSITIVE LOGITS
    DoubleQuotes
    0.69
    IsContent
    0.66
    ReusableCell
    0.64
    ValueGeneration
    0.62
    numerusform
    0.60
    NameInMap
    0.59
    matchCondition
    0.59
    QMetaType
    0.56
     AssemblyVersion
    0.55
    writeFieldEnd
    0.54
    Activations Density 0.004%

    No Known Activations