© 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. 43144
    Prev
    Next
    INDEX
    Explanations

    pleural

    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
    GraphicsUnit
    -1.03
    
    -0.92
    WebElementEntity
    -0.87
    OOTDTY
    -0.80
    Хьажоргаш
    -0.77
    actionMode
    -0.76
     wreaths
    -0.75
    Grüsse
    -0.73
    WithIOException
    -0.73
    adaptiveStyles
    -0.72
    POSITIVE LOGITS
    <h6>
    0.48
    https
    0.45
    rag
    0.43
    ed
    0.43
    ign
    0.42
    oles
    0.42
     br
    0.42
    na
    0.41
     مول
    0.41
    Permalink
    0.40
    Activations Density 1.131%

    No Known Activations