© 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. 0-CLT-HP
    7. 40146
    Prev
    Next
    INDEX
    Explanations

    research summaries

    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
    MigrationBuilder
    -0.80
    RTEE
    -0.73
     resourceCulture
    -0.72
    exitRule
    -0.72
     propOrder
    -0.71
    matchCondition
    -0.70
    WriteBarrier
    -0.67
     college
    -0.66
     "..\..\
    -0.66
    afficheront
    -0.65
    POSITIVE LOGITS
     olev
    0.52
    sterious
    0.52
    zyż
    0.49
    tadiene
    0.49
    колко
    0.49
    fromString
    0.48
    MLLoader
    0.45
    kepada
    0.45
    ofern
    0.45
    <bos>
    0.44
    Activations Density 0.196%

    No Known Activations