© 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. 94486
    Prev
    Next
    INDEX
    Explanations

    chair (person)

    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
    المكان
    -0.75
     JpaRepository
    -0.73
     InputDecoration
    -0.71
    ArrowToggle
    -0.71
    InputBorder
    -0.71
     تانيه
    -0.67
    chair
    -0.67
     Chair
    -0.66
    UnsafeEnabled
    -0.66
     Chairman
    -0.66
    POSITIVE LOGITS
    ing
    0.81
    ging
    0.58
    d
    0.51
    sch
    0.51
    dled
    0.48
    ding
    0.48
    ouss
    0.48
    isch
    0.47
    ising
    0.47
    ISCH
    0.47
    Activations Density 0.069%

    No Known Activations