© 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. 20-CLT-HP
    7. 78112
    Prev
    Next
    INDEX
    Explanations

    Code and software

    np_max-act-logits · 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
     Being
    -0.68
    Being
    -0.65
     Delivered
    -0.58
    áln
    -0.56
     Mein
    -0.55
    carried
    -0.55
    GraphicsUnit
    -0.55
    ">—
    -0.54
     ſtand
    -0.54
    Demografie
    -0.53
    POSITIVE LOGITS
    
    0.60
    tvguidetime
    0.57
    ViewFeatures
    0.50
     ins
    0.50
     presenting
    0.49
    uchtet
    0.46
     putting
    0.45
    ROIT
    0.45
    CloseOperation
    0.45
    WriteLiteral
    0.43
    Activations Density 0.001%

    No Known Activations