© 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. 2856
    Prev
    Next
    INDEX
    Explanations

    also

    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
     InputDecoration
    -0.76
    FormTagHelper
    -0.73
    "}")
    -0.67
    Hentet
    -0.66
    AddTagHelper
    -0.65
     חיצוניים
    -0.65
     >=",
    -0.60
     ProtoMessage
    -0.60
     BorderRadius
    -0.59
     TextAlign
    -0.59
    POSITIVE LOGITS
     the
    1.10
     those
    0.78
     (
    0.69
     our
    0.67
     other
    0.66
     of
    0.63
     their
    0.62
     some
    0.62
     –
    0.61
     others
    0.61
    Activations Density 0.001%

    No Known Activations