© 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. 6202
    Prev
    Next
    INDEX
    Explanations

    widespread

    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
    "}")
    -0.63
    '},
    -0.61
     BoxDecoration
    -0.58
    nissen
    -0.56
     lenker
    -0.55
    "}";
    -0.54
    oznam
    -0.53
    aarrggbb
    -0.52
    IndentedString
    -0.52
    IBOutlet
    -0.52
    POSITIVE LOGITS
     agreement
    0.65
    msgSender
    0.61
     recognition
    0.59
    RetentionPolicy
    0.59
     acknowledgement
    0.58
    agreement
    0.57
    recognition
    0.53
    EditPart
    0.53
     appreciation
    0.52
     disbelief
    0.51
    Activations Density 0.002%

    No Known Activations