© 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. 91014
    Prev
    Next
    INDEX
    Explanations

    Locations or institutions

    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
    tvguidetime
    -0.67
    mpotent
    -0.64
     sie
    -0.54
    quale
    -0.51
    mappedBy
    -0.50
    ByPrimaryKey
    -0.50
    ɵɵ
    -0.49
    bid
    -0.48
    bunal
    -0.47
     bid
    -0.47
    POSITIVE LOGITS
    seamnă
    0.88
     feroit
    0.72
     Efq
    0.72
     pleaſure
    0.69
    ſelf
    0.68
     Majefty
    0.66
     Monfieur
    0.66
     auroit
    0.65
     pouvoit
    0.65
     avoient
    0.63
    Activations Density 0.008%

    No Known Activations