© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6302
    Prev
    Next
    INDEX
    Explanations

    Code/technical instructions

    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
    Negative Logits
     '\\;'
    -0.75
     насељу
    -0.69
     "..\..\
    -0.67
     "..\..\..\
    -0.65
     doInBackground
    -0.63
     للمعارف
    -0.62
    nocache
    -0.61
     aikaa
    -0.60
    XmlAccessorType
    -0.57
    ,:);
    -0.57
    POSITIVE LOGITS
     swell
    0.66
     swells
    0.55
     to
    0.53
    swell
    0.52
     cresc
    0.52
     suspense
    0.52
     intensity
    0.51
     volume
    0.51
     swelling
    0.50
     excitement
    0.49
    Activations Density 0.007%

    No Known Activations