© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15769
    Prev
    Next
    INDEX
    Explanations

    bags

    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
     
    -0.52
     on
    -0.47
     -
    -0.46
    <tbody>
    -0.46
    ://
    -0.45
     I
    -0.43
     i
    -0.43
     (
    -0.42
     m
    -0.42
     V
    -0.42
    POSITIVE LOGITS
    Демографія
    1.03
    parsedMessage
    0.94
     propOrder
    0.94
     Monfieur
    0.93
    expandindo
    0.91
     Taktlose
    0.90
     beginnetje
    0.89
    MessageOf
    0.85
    Портали
    0.84
    NameInMap
    0.82
    Activations Density 0.014%

    No Known Activations