© 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. 78257
    Prev
    Next
    INDEX
    Explanations

    with

    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
    OGND
    -0.65
     démocr
    -0.63
     modalités
    -0.58
     préfé
    -0.57
    BeginInit
    -0.56
    enumi
    -0.55
    LookAnd
    -0.55
     étoit
    -0.53
     kasarigan
    -0.53
    PreferredItem
    -0.52
    POSITIVE LOGITS
    sle
    0.50
    reds
    0.49
    winds
    0.47
     InputDecoration
    0.46
    ives
    0.45
     Herzegovina
    0.45
    reuse
    0.45
    stick
    0.45
    lanes
    0.45
    sse
    0.45
    Activations Density 1.240%

    No Known Activations