© 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. 5-CLT-HP
    7. 4394
    Prev
    Next
    INDEX
    Explanations

    methods or options

    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
    awtextra
    -0.70
    TypedDataSet
    -0.65
     <>",
    -0.62
    ьаж
    -0.61
    riwal
    -0.60
     viewDidLoad
    -0.60
    ftagPool
    -0.60
    )";
    -0.60
    DataAnnotations
    -0.60
     GenerationType
    -0.59
    POSITIVE LOGITS
    KommentareTeilen
    0.69
     vicenda
    0.50
     réponse
    0.47
    .
    0.46
    out
    0.44
     resposta
    0.44
     karş
    0.43
    But
    0.43
     circonstances
    0.43
    狈
    0.42
    Activations Density 0.004%

    No Known Activations