© 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. 4524
    Prev
    Next
    INDEX
    Explanations

    beginning of document (or snippet)

    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
    bootstrapcdn
    -0.57
     <=",
    -0.52
    OGND
    -0.47
    NameInMap
    -0.47
    WebMethod
    -0.46
     ujednoznacz
    -0.46
     Italijani
    -0.46
    stb
    -0.45
    باط
    -0.45
     يتيمه
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.72
    enumi
    0.66
    RectangleBorder
    0.61
    pentry
    0.53
     ICommand
    0.52
    ษา
    0.52
    BoxShadow
    0.52
     Mung
    0.51
    enumii
    0.51
    BERGER
    0.50
    Activations Density 0.000%

    No Known Activations