© 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. 5-CLT-HP
    7. 688
    Prev
    Next
    INDEX
    Explanations

    conditional statements and questions

    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
    VIAF
    -0.79
    expandindo
    -0.77
     beginnetje
    -0.73
    kegaard
    -0.73
    routeProvider
    -0.68
    KURZBESCHREIBUNG
    -0.66
     дописавши
    -0.59
     سكانية
    -0.59
     eccl
    -0.59
     חיצוניים
    -0.59
    POSITIVE LOGITS
    –
    0.45
    -
    0.42
     (
    0.39
    —
    0.38
    ="<?=
    0.38
    ：　
    0.36
     două
    0.34
    —(
    0.33
    ‐
    0.33
    lucy
    0.32
    Activations Density 0.000%

    No Known Activations