© 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. 91348
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence fragments

    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
     дописавши
    -0.69
    parsedMessage
    -0.61
     CreateTagHelper
    -0.60
    ftagPool
    -0.60
    FieldBuilder
    -0.59
    tableFuture
    -0.58
    ">//
    -0.57
     beginnetje
    -0.54
     TestBed
    -0.54
    IUrlHelper
    -0.54
    POSITIVE LOGITS
     without
    0.52
    ÈS
    0.52
     affirm
    0.52
     categories
    0.51
     Viejo
    0.49
    getAge
    0.49
     all
    0.49
     Fø
    0.48
    WithContext
    0.47
    絶
    0.46
    Activations Density 0.001%

    No Known Activations