© 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. 1-CLT-HP
    7. 15343
    Prev
    Next
    INDEX
    Explanations

    ography

    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
    ography
    -1.20
     Bruno
    -0.71
    Bruno
    -0.61
    GRAPHY
    -0.46
    bruno
    -0.45
    ografía
    -0.43
    ografia
    -0.42
    ographic
    -0.42
    ografie
    -0.40
    igo
    -0.40
    POSITIVE LOGITS
    EDEFAULT
    0.91
     doubtnut
    0.81
    elerik
    0.79
     onPostExecute
    0.79
     linkovi
    0.76
    Espèce
    0.75
    #+#
    0.75
     utafitiHapana
    0.75
     Савез
    0.74
    anskje
    0.72
    Activations Density 0.132%

    No Known Activations