© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10848
    Prev
    Next
    INDEX
    Explanations

    laut

    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
    rowned
    -1.16
     Kurtz
    -1.13
     betweenstory
    -0.92
    pearance
    -0.87
     CreateTagHelper
    -0.87
    usto
    -0.82
    InSection
    -0.80
    aarrggbb
    -0.77
    structors
    -0.77
    laut
    -0.77
    POSITIVE LOGITS
     صوتيه
    0.46
     anticipate
    0.46
    omorphic
    0.46
    noinspection
    0.46
    länd
    0.44
     indict
    0.44
    IDAE
    0.44
    ILLON
    0.44
    لاح
    0.42
    iking
    0.41
    Activations Density 0.032%

    No Known Activations