© 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. 0-CLT-HP
    7. 90866
    Prev
    Next
    INDEX
    Explanations

    Ory

    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
    -1.13
     myſelf
    -1.13
     Houſe
    -1.10
     Diſ
    -1.05
     Monfieur
    -1.05
     Majefty
    -1.04
     Anſ
    -1.03
     itſelf
    -1.02
     Jefus
    -1.02
     Shakspeare
    -1.02
    POSITIVE LOGITS
    i
    0.85
    e
    0.84
    o
    0.82
    a
    0.81
    adi
    0.71
    ipe
    0.65
    rawDesc
    0.64
    eas
    0.62
    GeneratedCode
    0.61
    ه
    0.59
    Activations Density 0.083%

    No Known Activations