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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45683
    Prev
    Next
    INDEX
    Explanations

    dil

    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
     dil
    -1.03
    dil
    -0.96
     dilation
    -0.91
    Dil
    -0.80
     dilatation
    -0.72
     Dil
    -0.71
    dilation
    -0.69
     dilated
    -0.65
     dilution
    -0.59
     jScrollPane
    -0.57
    POSITIVE LOGITS
     صوتيه
    0.60
     Roskov
    0.59
    ("]");
    0.59
    Jeografia
    0.57
    ttemberg
    0.57
    utives
    0.55
     дописавши
    0.54
     programme
    0.54
     joint
    0.54
     Hole
    0.54
    Activations Density 0.009%

    No Known Activations