© 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. 95678
    Prev
    Next
    INDEX
    Explanations

    Inform

    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
    InjectAttribute
    -0.80
    setVerticalGroup
    -0.80
    findpost
    -0.78
    SharedDtor
    -0.78
    TagMode
    -0.76
     насељу
    -0.73
     NSCoder
    -0.71
     Signalez
    -0.69
    EndGlobalSection
    -0.69
    }]
    -0.68
    POSITIVE LOGITS
    BagConstraints
    0.47
    parametrize
    0.46
    arpa
    0.45
    ברס
    0.45
     tất
    0.45
     nationaux
    0.44
     Armed
    0.42
    Fonti
    0.42
    richtungen
    0.42
     sposób
    0.41
    Activations Density 0.066%

    No Known Activations