© 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. 6101
    Prev
    Next
    INDEX
    Explanations

    plans, ideas, questions

    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
     Efq
    -0.64
    WebVitals
    -0.60
     houſe
    -0.57
     fubject
    -0.55
     ſche
    -0.55
     alimentaires
    -0.53
     greateſt
    -0.53
     Theſe
    -0.53
    abestanden
    -0.52
    BASEPATH
    -0.52
    POSITIVE LOGITS
     emphasizes
    0.65
    setVerticalGroup
    0.63
     combines
    0.61
     incorporates
    0.61
    ritsar
    0.59
     was
    0.58
     places
    0.58
     promotes
    0.56
     emphasized
    0.56
    :✨
    0.56
    Activations Density 0.001%

    No Known Activations