© 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. 6233
    Prev
    Next
    INDEX
    Explanations

    Text excerpts/snippets

    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
     sanitaires
    -0.75
    AndEndTag
    -0.73
     resourceCulture
    -0.70
    しかない
    -0.68
    protoimpl
    -0.66
    esercito
    -0.64
     TextAppearance
    -0.62
     оригіналу
    -0.61
    contentLoaded
    -0.61
     financières
    -0.59
    POSITIVE LOGITS
    nub
    0.47
    UPAC
    0.46
    unno
    0.45
    apunov
    0.44
    หลาย
    0.43
     important
    0.42
    Key
    0.42
     key
    0.42
    ніше
    0.42
     etc
    0.42
    Activations Density 0.023%

    No Known Activations