© 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. 0-CLT-HP
    7. 95563
    Prev
    Next
    INDEX
    Explanations

    Inclu

    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
    Negative Logits
    providedIn
    -0.79
    sidemargin
    -0.79
    nonatomic
    -0.77
    RenderAtEndOf
    -0.77
    styleable
    -0.73
    帖最后由
    -0.71
    SceneManagement
    -0.70
    gameserver
    -0.69
    PropertyGroup
    -0.69
    ImageContext
    -0.68
    POSITIVE LOGITS
    s
    0.67
     renseignements
    0.52
     cantit
    0.51
    sika
    0.48
     quantités
    0.48
    sives
    0.47
     montagna
    0.47
     träd
    0.46
     espirituales
    0.46
     semelhantes
    0.46
    Activations Density 0.125%

    No Known Activations