© 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. 15105
    Prev
    Next
    INDEX
    Explanations

    meaning

    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
     enfans
    -0.76
     scolaires
    -0.72
     feroit
    -0.71
     greateſt
    -0.70
     pauvres
    -0.70
    uxxxx
    -0.69
     polvere
    -0.68
     inoxydable
    -0.68
     vectorielles
    -0.68
    évaluateur
    -0.68
    POSITIVE LOGITS
     B
    0.50
    stree
    0.48
     “
    0.47
     key
    0.46
     Key
    0.46
     Col
    0.46
      
    0.45
    ритори
    0.44
     
    0.44
     OMITTED
    0.44
    Activations Density 0.001%

    No Known Activations