© 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. 5-CLT-HP
    7. 4835
    Prev
    Next
    INDEX
    Explanations

    earn

    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
     Lightboxes
    -0.65
     noqa
    -0.60
    gonic
    -0.57
    phosa
    -0.57
    ituary
    -0.56
     Rel
    -0.56
    MessageTagHelper
    -0.55
    tvguidetime
    -0.55
    始
    -0.54
     insuffisamment
    -0.54
    POSITIVE LOGITS
    tymologie
    0.60
     enough
    0.57
     egna
    0.54
     majeurs
    0.53
     ENOUGH
    0.53
    enough
    0.52
     lycée
    0.52
    الإنجليزية
    0.51
     Inscrivez
    0.51
     egne
    0.51
    Activations Density 0.002%

    No Known Activations