© 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. 94965
    Prev
    Next
    INDEX
    Explanations

    charities

    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
     modes
    -0.74
    tvguidetime
    -0.71
    Autoritní
    -0.70
     industries
    -0.69
    migrationBuilder
    -0.68
    ed
    -0.65
    帖最后由
    -0.63
     CreateTagHelper
    -0.59
     disambiguazione
    -0.59
    Rüyada
    -0.59
    POSITIVE LOGITS
     femininas
    0.77
     dieux
    0.71
     fatica
    0.70
     détru
    0.69
     spesa
    0.69
     chré
    0.68
     femininos
    0.68
     supérieurs
    0.67
     étan
    0.66
     Grecs
    0.65
    Activations Density 0.104%

    No Known Activations