© 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. 1453
    Prev
    Next
    INDEX
    Explanations

    grammatical structures

    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
     MainAxisSize
    -0.77
    TagMode
    -0.68
    XmlAccessType
    -0.67
    protoc
    -0.64
     anhydride
    -0.63
    CppMethod
    -0.61
     doInBackground
    -0.60
     onPostExecute
    -0.60
    +#+#
    -0.60
    transQ
    -0.60
    POSITIVE LOGITS
     through
    0.89
    through
    0.70
     THROUGH
    0.58
     melalui
    0.58
     attraverso
    0.56
    Through
    0.56
     Through
    0.54
    getDoctrine
    0.53
    enschappe
    0.53
     thru
    0.53
    Activations Density 0.004%

    No Known Activations