© 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. 0-CLT-HP
    7. 42026
    Prev
    Next
    INDEX
    Explanations

    silicon

    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
     silicon
    -0.93
    enterOuterAlt
    -0.80
    Silicon
    -0.77
    kuuta
    -0.76
    تقاوى
    -0.74
    silicon
    -0.71
     Silicon
    -0.71
    曖昧さ回避
    -0.71
     متعلقه
    -0.69
    GIVEREF
    -0.68
    POSITIVE LOGITS
    ever
    0.64
    ep
    0.55
    ed
    0.54
    ik
    0.49
    AndEndTag
    0.49
    ew
    0.47
    ex
    0.47
    et
    0.46
    componentDid
    0.46
    ey
    0.45
    Activations Density 0.666%

    No Known Activations