© 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. 10394
    Prev
    Next
    INDEX
    Explanations

    locations, organizations, people

    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
    parsedMessage
    -0.87
    CppMethod
    -0.76
    SharedCtor
    -0.74
    Demografia
    -0.63
    ISupport
    -0.63
    MemoryWarning
    -0.59
     Efq
    -0.58
    IFO
    -0.57
    WithIOException
    -0.57
     puma
    -0.56
    POSITIVE LOGITS
    n
    0.47
    en
    0.47
    aarrggbb
    0.46
     Nau
    0.45
    i
    0.44
    an
    0.42
    dymyr
    0.42
    as
    0.42
    ing
    0.42
    ️
    0.41
    Activations Density 0.220%

    No Known Activations