© 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. 1-CLT-HP
    7. 15977
    Prev
    Next
    INDEX
    Explanations

    it

    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
     quelcon
    -0.57
     conmigo
    -0.55
     defStyle
    -0.54
     picioare
    -0.53
     makinesi
    -0.53
     asupra
    -0.53
     meisje
    -0.52
     obicei
    -0.52
    brainer
    -0.52
     malheureusement
    -0.52
    POSITIVE LOGITS
     evaluate
    0.61
     predict
    0.61
     show
    0.57
     ensure
    0.55
    ';
    0.54
     explain
    0.54
     lead
    0.54
     createState
    0.53
     dont
    0.53
     meet
    0.53
    Activations Density 0.078%

    No Known Activations