© 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. 91904
    Prev
    Next
    INDEX
    Explanations

    through

    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
    Personendaten
    -0.88
    WebElementEntity
    -0.61
    WithIOException
    -0.56
    UnusedPrivate
    -0.55
     QtCore
    -0.55
    +#+#
    -0.54
    RectangleBorder
    -0.53
    rasser
    -0.52
    lewati
    -0.52
    GraphicsUnit
    -0.51
    POSITIVE LOGITS
     a
    0.93
     several
    0.85
     an
    0.70
     numerous
    0.68
     many
    0.64
     some
    0.63
     two
    0.62
     another
    0.60
    several
    0.59
     few
    0.57
    Activations Density 0.004%

    No Known Activations