© 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. 14721
    Prev
    Next
    INDEX
    Explanations

    key parts

    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
    Highlights
    -0.77
     Highlights
    -0.64
    olia
    -0.60
     thạch
    -0.57
     HIGHLIGHTS
    -0.51
    er
    -0.47
    verlag
    -0.47
    anshi
    -0.47
     splicing
    -0.46
    qrstuvwxyz
    -0.46
    POSITIVE LOGITS
    DebuggerNonUser
    0.85
    CodedInputStream
    0.76
    MessageOf
    0.71
    AutoresizingMask
    0.69
     ErrIntOverflow
    0.68
    tvguidetime
    0.68
    MENAFN
    0.68
     विश्वसनीयता
    0.65
    FXMLLoader
    0.63
    SpringBootTest
    0.62
    Activations Density 0.006%

    No Known Activations