© 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. 0-CLT-HP
    7. 95077
    Prev
    Next
    INDEX
    Explanations

    scientific fragments

    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
    s
    -0.85
     har
    -0.72
    ers
    -0.60
     bar
    -0.58
     ven
    -0.58
     ver
    -0.57
     vie
    -0.56
    NameInMap
    -0.55
     lug
    -0.54
     le
    -0.54
    POSITIVE LOGITS
     avoient
    1.14
     auroit
    1.11
     feroit
    1.10
     étoient
    1.07
     étoit
    1.02
     anún
    0.97
    berdayakan
    0.91
     enfans
    0.91
     répon
    0.89
     scolaires
    0.89
    Activations Density 1.628%

    No Known Activations