© 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. 4-CLT-HP
    7. 1465
    Prev
    Next
    INDEX
    Explanations

    his

    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
    ivably
    -0.67
     ProtoMessage
    -0.66
     resourceCulture
    -0.66
    Batis
    -0.64
     typelib
    -0.63
    fillType
    -0.59
    ://$
    -0.59
     تضيفلها
    -0.58
    insee
    -0.58
    parsedMessage
    -0.58
    POSITIVE LOGITS
    <bos>
    0.54
    נטי
    0.47
     περ
    0.46
     resume
    0.45
    ınır
    0.45
    We
    0.45
     kita
    0.44
     We
    0.44
     complies
    0.44
     we
    0.43
    Activations Density 0.001%

    No Known Activations