© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3014
    Prev
    Next
    INDEX
    Explanations

    science and news

    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
    CloseOperation
    -0.74
     itſelf
    -0.59
     aihe
    -0.58
     Wikispecies
    -0.57
    帖最后由
    -0.54
     näky
    -0.54
     poffible
    -0.52
     Vikipedi
    -0.52
     riscal
    -0.52
    }\]
    -0.52
    POSITIVE LOGITS
    Rüyada
    0.63
    posedge
    0.63
     AssemblyVersion
    0.52
    LabelTagHelper
    0.51
    featureID
    0.49
    رشف
    0.49
     Exacts
    0.48
    exact
    0.46
     kis
    0.46
     exact
    0.46
    Activations Density 0.001%

    No Known Activations