© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 4479
    Prev
    Next
    INDEX
    Explanations

    (

    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
     and
    -0.85
     or
    -0.58
     see
    -0.54
     allá
    -0.52
     that
    -0.52
     oraz
    -0.52
    งาม
    -0.49
     AND
    -0.49
     그리고
    -0.48
     And
    -0.48
    POSITIVE LOGITS
    in
    0.67
    mybatisplus
    0.64
     protoimpl
    0.63
    by
    0.58
     typelib
    0.57
    on
    0.54
    at
    0.54
     NavController
    0.53
     AssemblyTitle
    0.53
    for
    0.53
    Activations Density 0.005%

    No Known Activations