© 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. 94641
    Prev
    Next
    INDEX
    Explanations

    question/relative pronouns

    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
     who
    -0.92
    .
    -0.76
    who
    -0.72
    -
    -0.70
     (
    -0.66
     Who
    -0.64
    (
    -0.63
    Who
    -0.60
     and
    -0.58
    /
    -0.58
    POSITIVE LOGITS
     Roskov
    1.16
     myſelf
    1.10
     AssemblyTitle
    1.02
     GenerationType
    1.00
     themſelves
    1.00
     itſelf
    1.00
     uſed
    0.99
    ^(@)
    0.95
     Shakspeare
    0.94
     chofe
    0.94
    Activations Density 0.119%

    No Known Activations