© 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. 20-CLT-HP
    7. 75797
    Prev
    Next
    INDEX
    Explanations

    couch

    np_max-act-logits · 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
     okuyayım
    -0.69
    
    -0.59
     ModelExpression
    -0.53
     Spéc
    -0.51
    Ifc
    -0.50
    Representation
    -0.50
    nelse
    -0.50
    yaf
    -0.49
    myra
    -0.48
    сылкі
    -0.47
    POSITIVE LOGITS
    حوالہ
    0.55
    GIVEREF
    0.52
    stands
    0.52
    hy
    0.51
    ob
    0.49
    hyr
    0.49
    liothèque
    0.48
    hogy
    0.48
     متعلقه
    0.47
     lilla
    0.47
    Activations Density 0.001%

    No Known Activations