© 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. 95255
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
     We
    -0.78
     Spisak
    -0.68
    lossians
    -0.67
    ranging
    -0.66
    nsics
    -0.66
    nourriture
    -0.65
    icitis
    -0.65
    HomeAsUp
    -0.64
    copg
    -0.63
    kyard
    -0.60
    POSITIVE LOGITS
    <bos>
    0.70
    “
    0.57
     heet
    0.52
    세
    0.51
    '[
    0.50
     Reſ
    0.49
     ſhall
    0.49
    稀
    0.49
     Perſ
    0.48
    ([...
    0.48
    Activations Density 0.071%

    No Known Activations