© 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. 20-CLT-HP
    7. 73229
    Prev
    Next
    INDEX
    Explanations

    technical or mixed text

    np_max-act-logits · 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
    RectangleBorder
    -0.66
     CSM
    -0.63
    BeginContext
    -0.58
    Cyfeiriadau
    -0.56
     Ties
    -0.56
     antif
    -0.54
     siè
    -0.54
     Jpa
    -0.53
     Shoe
    -0.52
    toBeDefined
    -0.52
    POSITIVE LOGITS
    LookAnd
    0.54
    verifyException
    0.49
     nic
    0.49
    lccn
    0.49
    ftagPool
    0.48
     Nic
    0.46
    reactstrap
    0.45
     समीक्षाओं
    0.45
    PreferredItem
    0.43
     "..\..\..\
    0.42
    Activations Density 0.000%

    No Known Activations