© 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. 0-CLT-HP
    7. 95462
    Prev
    Next
    INDEX
    Explanations

    atten

    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
    Not in Any Lists

    No Comments

    Negative Logits
     stället
    -0.88
     engraçadas
    -0.80
     varandra
    -0.77
     réguli
    -0.75
     sommar
    -0.74
    kjø
    -0.72
     vård
    -0.71
     strå
    -0.71
     summer
    -0.70
     colorés
    -0.70
    POSITIVE LOGITS
    ه
    0.69
    y
    0.65
    e
    0.60
    t
    0.58
    s
    0.57
    
    0.55
    a
    0.53
    tagHelperRunner
    0.52
     Kish
    0.52
    homonymie
    0.50
    Activations Density 0.041%

    No Known Activations