© 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. 14935
    Prev
    Next
    INDEX
    Explanations

    in

    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
    GOTREF
    -0.77
    HasForeignKey
    -0.67
    featureID
    -0.65
     Vikipedi
    -0.59
     disambiguazione
    -0.59
    }{*}{
    -0.58
     PSR
    -0.57
     Baillargeon
    -0.57
    TypedDataSet
    -0.56
    клопе
    -0.55
    POSITIVE LOGITS
     full
    0.59
     a
    0.54
     process
    0.53
     plain
    0.51
     case
    0.49
     action
    0.48
     an
    0.46
    المكان
    0.46
    comp
    0.46
    Action
    0.46
    Activations Density 0.008%

    No Known Activations