© 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. 8744
    Prev
    Next
    INDEX
    Explanations

    on

    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
     effects
    -0.66
    effects
    -0.61
     effect
    -0.60
    Effects
    -0.60
     Effects
    -0.58
    effect
    -0.57
     effetti
    -0.57
     efectos
    -0.54
    の効果
    -0.54
    effetto
    -0.52
    POSITIVE LOGITS
     himſelf
    0.84
     myſelf
    0.80
     nahilalakip
    0.79
     transfieras
    0.78
     themſelves
    0.77
     itſelf
    0.76
    новништво
    0.76
    ſelf
    0.74
    IntoConstraints
    0.74
     yourselves
    0.68
    Activations Density 0.032%

    No Known Activations