© 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. 20-CLT-HP
    7. 73544
    Prev
    Next
    INDEX
    Explanations

    pop

    np_max-act-logits · 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
     estimés
    -0.55
     ostavi
    -0.55
    AndEndTag
    -0.54
    SourceChecksum
    -0.54
     Италијани
    -0.52
    RRect
    -0.52
    IBar
    -0.51
    iral
    -0.50
     Zol
    -0.50
     विश्वसनीयता
    -0.50
    POSITIVE LOGITS
    poor
    0.49
    embang
    0.48
    Mozilla
    0.46
    WriteBarrier
    0.46
    󠁿
    0.46
     poor
    0.46
    ounid
    0.45
    MCH
    0.44
     cérami
    0.44
    etcode
    0.44
    Activations Density 0.000%

    No Known Activations