© 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. 72633
    Prev
    Next
    INDEX
    Explanations

    Code-related terms

    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
    nights
    -0.67
    night
    -0.57
    Raum
    -0.56
     duquel
    -0.56
     the
    -0.56
    CLUYE
    -0.55
    touch
    -0.55
    NIGHT
    -0.55
    SHAPE
    -0.54
    Bureau
    -0.53
    POSITIVE LOGITS
    MigrationBuilder
    0.58
    ftagPool
    0.54
    AddTagHelper
    0.54
    GOTREF
    0.52
    AnchorStyles
    0.47
     onOptions
    0.44
    WebVitals
    0.44
    GraphicsUnit
    0.43
    ContentAsync
    0.41
    biam
    0.40
    Activations Density 0.001%

    No Known Activations