© 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. 9878
    Prev
    Next
    INDEX
    Explanations

    eaten

    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
     knex
    -0.47
    here
    -0.47
    IsUnicode
    -0.46
    let
    -0.45
    span
    -0.45
    CompoundButton
    -0.45
    cshtml
    -0.44
    man
    -0.43
     sorgfäl
    -0.43
    dziew
    -0.42
    POSITIVE LOGITS
     continúas
    0.65
     popular
    0.59
     Popular
    0.57
     Privacidade
    0.56
     gainera
    0.56
    gantes
    0.56
     ZA
    0.53
    publ
    0.53
     faſt
    0.53
     Comfort
    0.52
    Activations Density 0.003%

    No Known Activations