© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    Code/technical/scientific text

    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
    DockStyle
    -0.75
    amaño
    -0.68
    osť
    -0.59
    umenten
    -0.57
     joaat
    -0.57
    optera
    -0.57
    =$?
    -0.56
    ביוגרפיה
    -0.56
    SBATCH
    -0.55
     ddelweddau
    -0.55
    POSITIVE LOGITS
    oredCriteria
    0.63
    featureID
    0.54
    StoryboardSegue
    0.52
     fuch
    0.52
     InputDecoration
    0.49
    stino
    0.49
    орк
    0.49
     TextInputType
    0.48
    AsUp
    0.47
     HasFactory
    0.47
    Activations Density 0.000%

    No Known Activations