© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91179
    Prev
    Next
    INDEX
    Explanations

    could

    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
     للمعارف
    -0.90
     متعلقه
    -0.73
    RenderAtEndOf
    -0.70
    CodedInputStream
    -0.68
    InputTagHelper
    -0.68
    mybatisplus
    -0.68
    principalColumn
    -0.68
     CreateTagHelper
    -0.67
    UrlResolution
    -0.65
     snippetHide
    -0.63
    POSITIVE LOGITS
     the
    0.52
     val
    0.48
     Abar
    0.47
    łat
    0.44
    mely
    0.43
    appartamento
    0.43
    Bakgrunnsstoff
    0.43
    RoomId
    0.43
    ÁF
    0.42
     Ab
    0.41
    Activations Density 0.003%

    No Known Activations