© 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. 15417
    Prev
    Next
    INDEX
    Explanations

    ans

    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
    principalColumn
    -0.65
    utched
    -0.61
     racines
    -0.60
    AnchorTagHelper
    -0.60
     "..\..\
    -0.59
    ITHUB
    -0.59
     vôtre
    -0.58
     Hero
    -0.58
     NSCoder
    -0.58
     étan
    -0.57
    POSITIVE LOGITS
    protoimpl
    0.60
    ress
    0.50
    er
    0.50
    DataAnnotations
    0.49
    ing
    0.48
    ten
    0.48
    dom
    0.47
     Independiente
    0.45
    i
    0.44
    in
    0.44
    Activations Density 0.093%

    No Known Activations