© 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. 76565
    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
    Datuak
    -0.64
    ThroughAttribute
    -0.62
     cherchés
    -0.55
     snippetHide
    -0.54
    OGND
    -0.51
    ::::::::
    -0.51
    BeginContext
    -0.50
    AndEndTag
    -0.49
    ագրություններ
    -0.47
     Վերցված
    -0.47
    POSITIVE LOGITS
     BoxFit
    0.52
    tar
    0.52
     Tuhan
    0.51
    andro
    0.51
    paths
    0.51
    rophoresis
    0.50
    pecially
    0.48
    ánicas
    0.48
    lizes
    0.47
    忘
    0.47
    Activations Density 0.003%

    No Known Activations