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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38579
    Prev
    Next
    INDEX
    Explanations

    tif

    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
    hæng
    -0.85
     automatiques
    -0.82
     Grecs
    -0.82
     rêves
    -0.75
     néz
    -0.73
     détru
    -0.72
     feroit
    -0.72
     avoient
    -0.71
     relatifs
    -0.71
     igenom
    -0.71
    POSITIVE LOGITS
    ,
    0.68
    .
    0.59
     or
    0.57
     —
    0.54
     ad
    0.54
    !
    0.53
     (
    0.52
     ba
    0.51
    ses
    0.51
    ?
    0.50
    Activations Density 0.109%

    No Known Activations