© 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. 43746
    Prev
    Next
    INDEX
    Explanations

    numbers/periods/punctuation

    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
     الحره
    -0.50
    Clik
    -0.45
     Kard
    -0.44
     Hi
    -0.43
    geführten
    -0.43
    findpost
    -0.42
    afficheront
    -0.42
    busch
    -0.42
    ッキリ
    -0.42
    Hochspringen
    -0.41
    POSITIVE LOGITS
     AssemblyTitle
    0.79
    brtc
    0.70
    RunAsync
    0.67
    /*
    0.67
     <<<<<<<<<<<<<<
    0.65
    spesies
    0.63
     AspNetCore
    0.63
     بيها
    0.62
     skewers
    0.59
    TagHelper
    0.58
    Activations Density 0.120%

    No Known Activations