© 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. 5-CLT-HP
    7. 91784
    Prev
    Next
    INDEX
    Explanations

    geography

    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
    <>());
    -0.56
     FormBuilder
    -0.53
    apimachinery
    -0.52
    <bos>
    -0.50
    ׂ
    -0.49
    談社
    -0.48
    openqa
    -0.47
    otropic
    -0.46
    obed
    -0.46
    RIED
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.71
     autorytatywna
    0.65
    Koordinaten
    0.59
     montagna
    0.58
     Normdatei
    0.57
     fevere
    0.56
     sonno
    0.56
    TintMode
    0.56
     spectateurs
    0.55
     tournage
    0.54
    Activations Density 0.000%

    No Known Activations