© 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. 5993
    Prev
    Next
    INDEX
    Explanations

    Identification cards or code

    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
    \{\\
    -0.61
    IntoConstraints
    -0.61
    RenderAtEndOf
    -0.59
     themſelves
    -0.57
     Jefus
    -0.56
     poffible
    -0.56
     bezeichneter
    -0.55
     leaſt
    -0.55
    BagConstraints
    -0.53
     bachelor
    -0.52
    POSITIVE LOGITS
    bcryptjs
    0.62
    Nationalité
    0.56
     resourceCulture
    0.54
     لينك
    0.51
     Enrollment
    0.49
    penup
    0.49
     Identity
    0.48
     Card
    0.47
     Identities
    0.46
    setViewportView
    0.46
    Activations Density 0.002%

    No Known Activations