© 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. 78003
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Brüder
    -0.46
    blok
    -0.42
    fulness
    -0.40
     blocked
    -0.40
    aited
    -0.40
     irm
    -0.39
     blok
    -0.39
     block
    -0.39
     narrated
    -0.39
     slabs
    -0.39
    POSITIVE LOGITS
    HasAnnotation
    0.60
    protoc
    0.58
    photobucket
    0.57
    jspb
    0.57
    OGND
    0.56
     uintptr
    0.55
    Parcelize
    0.55
     وتسجيلات
    0.54
    ipedi
    0.54
     localVar
    0.53
    Activations Density 0.002%

    No Known Activations