© 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. 4-CLT-HP
    7. 335
    Prev
    Next
    INDEX
    Explanations

    across

    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
     newBuilder
    -0.65
     оригіналу
    -0.61
    COUVER
    -0.56
     Bioaccumulative
    -0.52
    Géographie
    -0.50
    NUMX
    -0.50
     mergeFrom
    -0.49
     itſelf
    -0.49
    unking
    -0.48
    MessageDigest
    -0.48
    POSITIVE LOGITS
     estekak
    0.66
     समीक्षक
    0.60
    Оп
    0.58
    .*")]
    0.57
    anglès
    0.56
    Hauptartikel
    0.54
     ligiloj
    0.52
     disciplines
    0.51
     specialties
    0.50
    idenav
    0.50
    Activations Density 0.002%

    No Known Activations