© 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. 43359
    Prev
    Next
    INDEX
    Explanations

    variety of topics

    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
     Reſ
    -1.07
     Anſ
    -1.04
     houſe
    -1.02
     purpoſe
    -1.02
     Houſe
    -0.99
     reaſon
    -0.98
     Inſ
    -0.94
     Diſ
    -0.94
     uſe
    -0.94
     pleaſure
    -0.93
    POSITIVE LOGITS
    principalTable
    1.09
    MigrationBuilder
    1.04
    LookAnd
    1.02
     ProtoMessage
    0.96
     Taktlose
    0.94
    contentLoaded
    0.91
    parsedMessage
    0.88
    GEBURTSDATUM
    0.88
    webElementGuid
    0.87
    SequentialGroup
    0.86
    Activations Density 0.164%

    No Known Activations