© 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. 1-CLT-HP
    7. 9278
    Prev
    Next
    INDEX
    Explanations

    class

    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
     مرئيه
    -0.53
    BeginContext
    -0.49
     يتيمه
    -0.48
    ULI
    -0.48
    ΤΗ
    -0.47
    ErrorListener
    -0.47
    ctivos
    -0.47
     culturali
    -0.47
    pic
    -0.47
    uli
    -0.47
    POSITIVE LOGITS
    WithIOException
    0.62
    verwijspagina
    0.60
    LookAnd
    0.60
    rungsseite
    0.57
    IndentedString
    0.54
    RTLD
    0.54
    endphp
    0.53
     treating
    0.51
    kháu
    0.51
    AndEndTag
    0.48
    Activations Density 0.011%

    No Known Activations