© 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. 76872
    Prev
    Next
    INDEX
    Explanations

    A

    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
    rätt
    -0.46
     båda
    -0.46
     наук
    -0.43
    ee
    -0.41
     puissent
    -0.39
     tillbaka
    -0.39
    koliv
    -0.39
    gräns
    -0.39
     fleste
    -0.38
     lær
    -0.38
    POSITIVE LOGITS
    UserScript
    0.86
     GenerationType
    0.84
    AnchorStyles
    0.80
    elemField
    0.75
     Exacts
    0.75
    tagHelperRunner
    0.70
    SourceChecksum
    0.69
    Демографія
    0.69
    WebElementEntity
    0.68
     ExecuteAsync
    0.68
    Activations Density 0.007%

    No Known Activations