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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 964
    Prev
    Next
    INDEX
    Explanations

    with

    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
    sizeCache
    -0.68
    Bioaccumulative
    -0.55
    Література
    -0.53
     and
    -0.49
     Вікі
    -0.48
     this
    -0.46
     mert
    -0.45
     or
    -0.45
     springfox
    -0.45
     ostavi
    -0.44
    POSITIVE LOGITS
     other
    0.72
    other
    0.62
    otras
    0.60
    Other
    0.59
    autres
    0.58
     husbands
    0.57
    manship
    0.56
     بيها
    0.56
     otras
    0.55
    autre
    0.55
    Activations Density 0.029%

    No Known Activations