© 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. 4-CLT-HP
    7. 1148
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ADELPHIA
    -0.50
    OGND
    -0.50
    createTextNode
    -0.47
    IZABETH
    -0.47
     TextAppearance
    -0.47
    جغرافيا
    -0.46
    TagHelper
    -0.45
    InSection
    -0.44
     resultCode
    -0.44
    Personendaten
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.64
     Coaches
    0.57
     Cervical
    0.55
     Contractors
    0.54
     Authors
    0.54
     Impact
    0.54
     Drinking
    0.53
     Reflex
    0.53
     Particularly
    0.52
     Toward
    0.52
    Activations Density 0.021%

    No Known Activations