© 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. 1-CLT-HP
    7. 45940
    Prev
    Next
    INDEX
    Explanations

    spect

    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
     Ritchie
    -0.76
    imoto
    -0.60
    nger
    -0.53
     Rossi
    -0.52
     Trá
    -0.52
    Зноскі
    -0.50
    Mixed
    -0.49
     seh
    -0.49
    Sze
    -0.48
     Sentin
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    0.75
    featureID
    0.72
    -------
    0.69
    TintMode
    0.68
    SourceChecksum
    0.66
    MessageOf
    0.65
     Meksiku
    0.63
    IUrlHelper
    0.62
    دانشنامهٔ
    0.60
     himo
    0.57
    Activations Density 0.183%

    No Known Activations