© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2420
    Prev
    Next
    INDEX
    Explanations

    silicon/silica

    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
    pack
    -0.52
    gdx
    -0.52
    kkue
    -0.52
    <bos>
    -0.48
     McColl
    -0.46
    บุ
    -0.45
    指令
    -0.45
    peer
    -0.44
    InlineData
    -0.44
    rai
    -0.44
    POSITIVE LOGITS
     fevere
    0.66
    silicon
    0.65
    VersionUID
    0.60
     silica
    0.60
     ویکی‌پدیای
    0.59
    ($__
    0.59
     StatefulWidget
    0.59
     silic
    0.58
    AnimationsModule
    0.58
     silicate
    0.57
    Activations Density 0.056%

    No Known Activations