© 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. 20-CLT-HP
    7. 71777
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    rmtree
    -0.61
     NSCoder
    -0.60
    ResumeLayout
    -0.58
    Proverbs
    -0.53
    SuspendLayout
    -0.52
     مرئيه
    -0.52
    #+#
    -0.51
     Prov
    -0.51
    oston
    -0.51
     урна
    -0.50
    POSITIVE LOGITS
    راسیون
    0.52
    Jereo
    0.52
     Distrito
    0.50
    XMLSchema
    0.49
    audiovisuel
    0.48
     Waray
    0.46
    olev
    0.46
    chol
    0.45
    retries
    0.45
    ngdoc
    0.44
    Activations Density 0.002%

    No Known Activations