© 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. 1-CLT-HP
    7. 14449
    Prev
    Next
    INDEX
    Explanations

    "woven" or the word "mean"

    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
    fjspx
    -0.69
    Portale
    -0.63
    NameInMap
    -0.57
     pageContext
    -0.55
    $^{
    -0.54
    LookAnd
    -0.52
    ngdoc
    -0.51
    seamnă
    -0.50
     beginnetje
    -0.49
    typeorm
    -0.49
    POSITIVE LOGITS
     that
    0.57
     Gabel
    0.51
     righteousness
    0.50
     scouts
    0.50
    ὖ
    0.50
     للمعارف
    0.50
     хорошем
    0.50
     mouths
    0.50
     darkness
    0.49
     Thread
    0.48
    Activations Density 0.020%

    No Known Activations