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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1191
    Prev
    Next
    INDEX
    Explanations

    Less than sign

    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
     Himo
    -1.00
    UserScript
    -0.97
     betweenstory
    -0.94
    batore
    -0.93
    AndEndTag
    -0.88
     obstante
    -0.85
     مرئيه
    -0.83
    ToBounds
    -0.82
    TypedDataSet
    -0.82
    InputTagHelper
    -0.81
    POSITIVE LOGITS
     the
    0.70
     
    0.68
     a
    0.68
    ↵
    0.65
    .
    0.65
    ↵↵
    0.59
     I
    0.59
    <bos>
    0.58
    ).
    0.57
     The
    0.54
    Activations Density 0.015%

    No Known Activations