© 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. 91033
    Prev
    Next
    INDEX
    Explanations

    disappoint

    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
     unknownFields
    -0.60
    nologue
    -0.59
    EndProject
    -0.51
    sediaan
    -0.51
     Signalez
    -0.50
    haja
    -0.49
    Życiorys
    -0.49
    nalpot
    -0.48
     transfieras
    -0.48
     szabad
    -0.48
    POSITIVE LOGITS
    findpost
    0.62
     resourceCulture
    0.55
    sizeCache
    0.52
     ویکی‌پدیای
    0.52
    djangoproject
    0.52
    protoimpl
    0.50
    MockMvc
    0.50
    bootstrapcdn
    0.50
     Kuba
    0.49
    ùm
    0.48
    Activations Density 0.001%

    No Known Activations