© 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. 4-CLT-HP
    7. 106
    Prev
    Next
    INDEX
    Explanations

    up

    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
    <bos>
    -0.84
     spalle
    -0.53
    țiunea
    -0.47
    彼が
    -0.45
     hoofd
    -0.43
     ambientales
    -0.42
    çon
    -0.40
    naver
    -0.40
     sauver
    -0.40
    getBy
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.87
    tagHelperRunner
    0.82
     disponibilités
    0.79
     متعلقه
    0.76
    }{*}{}
    0.73
    endphp
    0.72
    setVerticalGroup
    0.72
     externi
    0.70
    }{*}{
    0.69
     estekak
    0.69
    Activations Density 0.001%

    No Known Activations