© 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. 73149
    Prev
    Next
    INDEX
    Explanations

    cassette

    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
     '\\;'
    -0.81
     distanciation
    -0.66
     calendriers
    -0.61
     Gans
    -0.61
    MigrationBuilder
    -0.59
    LookAnd
    -0.58
    hyrchwyd
    -0.57
     lenker
    -0.56
    xase
    -0.56
     JpaRepository
    -0.55
    POSITIVE LOGITS
    ENODEV
    0.54
     ages
    0.53
     age
    0.50
    ilesh
    0.49
     sixties
    0.47
    InputTagHelper
    0.47
     seventies
    0.47
     hot
    0.46
    AndEndTag
    0.46
    ages
    0.45
    Activations Density 0.001%

    No Known Activations