© 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. 9777
    Prev
    Next
    INDEX
    Explanations

    blind

    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
     Taktlose
    -0.61
    webElementGuid
    -0.58
    çais
    -0.53
    ofire
    -0.51
    δας
    -0.50
    SqlClient
    -0.48
    ("}\
    -0.48
    Lähteet
    -0.47
     blind
    -0.47
    ControllerTest
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    0.60
     المعيارى
    0.52
     ModelExpression
    0.52
    цездатний
    0.50
    发表于
    0.49
    شهاد
    0.49
    MigrationBuilder
    0.49
    GetEnumerator
    0.48
     beggar
    0.48
     onOptions
    0.46
    Activations Density 0.024%

    No Known Activations