© 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. 0-CLT-HP
    7. 95557
    Prev
    Next
    INDEX
    Explanations

    hobbies and crafts

    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
     pleaſure
    -1.13
     myſelf
    -1.06
     reaſon
    -1.04
     himſelf
    -1.00
     purpoſe
    -1.00
     fevere
    -0.96
     Efq
    -0.95
     ſta
    -0.93
     ſhe
    -0.93
     ſever
    -0.93
    POSITIVE LOGITS
     
    0.62
     for
    0.56
    '
    0.56
     to
    0.53
     "
    0.51
     With
    0.51
     s
    0.49
    }
    0.49
    ↵
    0.48
     A
    0.48
    Activations Density 0.033%

    No Known Activations