© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75634
    Prev
    Next
    INDEX
    Explanations

    family

    np_max-act-logits · 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
     autorytatywna
    -0.73
    tvguidetime
    -0.61
    icordia
    -0.60
    RenderAtEndOf
    -0.60
    awtextra
    -0.59
    andExpect
    -0.58
    IndentedString
    -0.57
    scalatest
    -0.56
     gốc
    -0.53
    elcome
    -0.52
    POSITIVE LOGITS
     family
    0.56
    family
    0.52
    -
    0.51
     Cur
    0.48
    DataBind
    0.46
     Insee
    0.44
     Kur
    0.44
    desh
    0.43
     kül
    0.43
     preuves
    0.42
    Activations Density 0.001%

    No Known Activations