© 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. 5-CLT-HP
    7. 92836
    Prev
    Next
    INDEX
    Explanations

    Sydney

    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
    .
    -0.66
    gdx
    -0.46
    equalsIgnoreCase
    -0.45
     exacerbated
    -0.42
    ;
    -0.41
    <eos>
    -0.40
     plus
    -0.39
     versus
    -0.39
     ===
    -0.38
    ibm
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.94
    KURZBESCHREIBUNG
    0.91
     autorytatywna
    0.87
    دانشنامهٔ
    0.86
     utafitiHapana
    0.86
    AndEndTag
    0.86
    ⓧ
    0.85
     chi̍t
    0.82
    SourceChecksum
    0.79
    aarrggbb
    0.75
    Activations Density 0.002%

    No Known Activations