© 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. 5-CLT-HP
    7. 94108
    Prev
    Next
    INDEX
    Explanations

    headline

    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
     يتيمه
    -0.76
    RenderAtEndOf
    -0.68
     sarili
    -0.54
    AddTagHelper
    -0.49
    saraba
    -0.47
     utafitiHapana
    -0.45
     moindre
    -0.44
     sacré
    -0.44
     tendre
    -0.41
     spirituale
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.80
     meanwhile
    0.75
     inoltre
    0.72
    Ecotoxicity
    0.72
     Réponses
    0.71
    tvguidetime
    0.69
     متعلقه
    0.68
    +#+#
    0.68
    tonode
    0.65
    ervant
    0.63
    Activations Density 0.015%

    No Known Activations