© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76345
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text

    np_max-act-logits · 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
    principalColumn
    -0.78
     autorytatywna
    -0.69
    DockStyle
    -0.67
    writeField
    -0.65
    :✨
    -0.64
    TypedDataSet
    -0.62
    WriteTagHelper
    -0.60
    ⓧ
    -0.59
     opérés
    -0.59
    oa̍t
    -0.58
    POSITIVE LOGITS
    åringen
    0.42
    apl
    0.42
     trời
    0.40
    fontName
    0.39
    VILLE
    0.38
    ONIA
    0.38
     strictement
    0.38
    plate
    0.38
     yoda
    0.38
     Bhat
    0.38
    Activations Density 0.000%

    No Known Activations