© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41293
    Prev
    Next
    INDEX
    Explanations

    jeopardy

    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
    y
    -0.71
    d
    -0.58
    ying
    -0.56
    ry
    -0.54
    er
    -0.53
    s
    -0.53
    n
    -0.52
    entiary
    -0.51
    inne
    -0.51
    anager
    -0.50
    POSITIVE LOGITS
     purpoſe
    0.76
     Conſ
    0.73
     houſe
    0.71
     themſelves
    0.70
     Diſ
    0.69
     Reſ
    0.69
     ſta
    0.69
    windowFixed
    0.68
     poffe
    0.68
    ]")]
    0.68
    Activations Density 0.337%

    No Known Activations