© 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. 1-CLT-HP
    7. 15688
    Prev
    Next
    INDEX
    Explanations

    atrophy

    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
    WebMethod
    -0.49
    DeltaTime
    -0.47
     bezeichneter
    -0.47
    ViewSet
    -0.46
    Migrations
    -0.46
     check
    -0.46
     desic
    -0.46
    TestBed
    -0.45
    Datuak
    -0.45
     formation
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.62
    tagHelperRunner
    0.59
     propOrder
    0.57
     Roskov
    0.54
     ویکی‌آمباردا
    0.54
    возмо
    0.52
     oprot
    0.52
    quely
    0.51
     simplifié
    0.50
    umblr
    0.49
    Activations Density 0.009%

    No Known Activations