© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11568
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    +#+#
    -0.61
    ValueStyle
    -0.60
    TabIndex
    -0.55
     throw
    -0.53
    enterOuterAlt
    -0.52
     Madeline
    -0.51
     Insight
    -0.50
     Nix
    -0.50
    Geografi
    -0.48
     Strap
    -0.48
    POSITIVE LOGITS
    +:+
    0.66
    audrait
    0.62
      (
    0.60
     typelib
    0.58
    #
    0.57
    kháu
    0.57
    saraba
    0.55
    makeConstraints
    0.54
    nezeu
    0.53
    tslib
    0.52
    Activations Density 0.008%

    No Known Activations