© 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. 9762
    Prev
    Next
    INDEX
    Explanations

    ours

    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
     فريبيس
    -0.65
     الحره
    -0.57
    TestingModule
    -0.54
     supérieures
    -0.53
     loisirs
    -0.53
     nôtre
    -0.51
     felizes
    -0.49
     lccn
    -0.49
     termica
    -0.49
     déri
    -0.49
    POSITIVE LOGITS
    mybatisplus
    0.60
    weed
    0.55
    piece
    0.54
    frost
    0.54
    anship
    0.54
    fur
    0.53
    head
    0.52
    oid
    0.52
    PreferredItem
    0.52
    proof
    0.51
    Activations Density 0.022%

    No Known Activations