© 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. 9402
    Prev
    Next
    INDEX
    Explanations

    Islamic

    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
    ReusableCell
    -0.71
    存于互联网档案馆
    -0.58
     الحره
    -0.58
    ApiProperty
    -0.54
    MigrationBuilder
    -0.53
    LoS
    -0.53
     AssemblyCulture
    -0.53
    DialogContent
    -0.53
    agascar
    -0.52
    TagMode
    -0.52
    POSITIVE LOGITS
    dominal
    0.48
     Revolución
    0.47
    (@"%@",
    0.46
     "..\..\..\
    0.45
     Wiking
    0.45
     accompli
    0.43
     Auss
    0.43
     Revolution
    0.43
    Fé
    0.42
     Financi
    0.41
    Activations Density 0.071%

    No Known Activations