© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11646
    Prev
    Next
    INDEX
    Explanations

    animals or Oklahoma

    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
     Pickering
    -1.01
     Encounter
    -0.75
    GraphicsUnit
    -0.71
    ensch
    -0.70
     ExecuteAsync
    -0.69
    endphp
    -0.69
    ⓧ
    -0.68
     للمعارف
    -0.68
     Zyg
    -0.67
     InputDecoration
    -0.66
    POSITIVE LOGITS
     mergeFrom
    0.56
    HandlerContext
    0.44
    UG
    0.43
     Hel
    0.43
    hoeddwyd
    0.42
     ge
    0.42
     E
    0.42
    utm
    0.41
    wedge
    0.41
     Gef
    0.41
    Activations Density 0.026%

    No Known Activations