© 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. 0-CLT-HP
    7. 42962
    Prev
    Next
    INDEX
    Explanations

    setting

    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
    DoubleQuotes
    -0.82
    äsident
    -0.66
    BuilderFactory
    -0.65
    glMatrixMode
    -0.65
    SequentialGroup
    -0.64
    ."],
    -0.64
    lgari
    -0.64
    ecake
    -0.63
     AssemblyProduct
    -0.62
     '\\;'
    -0.61
    POSITIVE LOGITS
    TagMode
    0.56
     forState
    0.45
     anzi
    0.45
     compter
    0.44
    הערות
    0.44
     of
    0.43
     option
    0.43
     määrä
    0.43
    nEnter
    0.43
     Option
    0.43
    Activations Density 0.641%

    No Known Activations