© 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. 20-CLT-HP
    7. 72418
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Schul
    -0.47
    tagext
    -0.46
    ="_
    -0.44
    Dougall
    -0.43
    ))^
    -0.42
    )^(
    -0.41
    ->_
    -0.41
    )、
    -0.40
    ционного
    -0.39
    ESCO
    -0.39
    POSITIVE LOGITS
     resourceCulture
    0.73
     виправивши
    0.64
    Diweddarwch
    0.64
    
    0.57
    athione
    0.57
    TRIBUN
    0.57
     Inactive
    0.56
     препратки
    0.56
     tyrosine
    0.54
    poptosis
    0.54
    Activations Density 0.003%

    No Known Activations