© 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. 6005
    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
    StoryboardSegue
    -0.69
    AndEndTag
    -0.68
    ScopeManager
    -0.62
    findpost
    -0.59
     InputDecoration
    -0.58
     CreateTagHelper
    -0.57
     établi
    -0.56
     remercie
    -0.56
     rayures
    -0.56
     propOrder
    -0.55
    POSITIVE LOGITS
     calendar
    0.48
     phase
    0.47
    frastructure
    0.46
     hypo
    0.45
    nefs
    0.44
     anhydrous
    0.44
    blende
    0.43
     purity
    0.43
     nup
    0.43
    ---+
    0.43
    Activations Density 0.003%

    No Known Activations