© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45798
    Prev
    Next
    INDEX
    Explanations

    Perl

    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
    LS
    -0.94
    LC
    -0.88
     LC
    -0.73
     LS
    -0.64
    queryInterface
    -0.58
    localctx
    -0.56
    Ls
    -0.55
    setVerticalGroup
    -0.54
    clc
    -0.53
    lc
    -0.51
    POSITIVE LOGITS
    IVEREF
    0.54
     Rides
    0.50
    ynos
    0.50
    лтемелер
    0.48
    astéro
    0.48
    աստ
    0.48
     Volley
    0.48
     Leaving
    0.48
     Penalty
    0.47
    ceeds
    0.47
    Activations Density 0.114%

    No Known Activations