© 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. 2328
    Prev
    Next
    INDEX
    Explanations

    likely

    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
     SwitchCompat
    -0.59
    archiviato
    -0.57
    GraphicsUnit
    -0.53
    IsContent
    -0.52
     useParams
    -0.52
     bäst
    -0.50
    AccessorTable
    -0.49
     endblock
    -0.48
    Beste
    -0.48
    ="@+
    -0.48
    POSITIVE LOGITS
     shaken
    0.59
     interrupted
    0.57
    unconfirmed
    0.56
     Saxons
    0.56
     annotated
    0.56
     discouraged
    0.54
     stunned
    0.54
     distracted
    0.53
     burdened
    0.53
     dazed
    0.53
    Activations Density 0.001%

    No Known Activations