© 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. 8724
    Prev
    Next
    INDEX
    Explanations

    yaw

    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
    setVerticalGroup
    -0.75
     IBOutlet
    -0.73
    AndEndTag
    -0.71
    AutoScale
    -0.67
    findpost
    -0.66
     Мексичка
    -0.65
    Diweddarwch
    -0.65
     endfor
    -0.60
     betweenstory
    -0.60
    ImageContext
    -0.57
    POSITIVE LOGITS
    Przypisy
    0.51
     pad
    0.49
    syn
    0.48
     Pad
    0.48
    SUNG
    0.47
    esterol
    0.47
    thington
    0.47
     Red
    0.46
    zzarella
    0.46
     Pr
    0.45
    Activations Density 0.047%

    No Known Activations