© 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. 0-CLT-HP
    7. 43137
    Prev
    Next
    INDEX
    Explanations

    cloth or possibility

    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
     cloth
    -2.55
    cloth
    -2.47
     Cloth
    -2.25
    Cloth
    -1.96
     CLOTH
    -1.35
     cloths
    -1.31
    cloths
    -1.25
     paño
    -0.88
     négociations
    -0.75
     پارچه
    -0.71
    POSITIVE LOGITS
    !*\
    0.61
    ier
    0.59
    iest
    0.53
    ie
    0.50
    ies
    0.47
     relevant
    0.45
    ill
    0.45
    ships
    0.45
    掴
    0.44
    ines
    0.44
    Activations Density 0.184%

    No Known Activations