© 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. 95466
    Prev
    Next
    INDEX
    Explanations

    spire

    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
     spire
    -1.53
     Spire
    -1.13
    phate
    -1.08
    Spire
    -0.77
    spire
    -0.77
    Personensuche
    -0.59
    })*/
    -0.57
    Aktualisiert
    -0.56
     BSA
    -0.55
     متعلقه
    -0.53
    POSITIVE LOGITS
     BorderSide
    0.65
    lles
    0.53
     useParams
    0.52
    ttino
    0.52
     AppComponent
    0.50
    awakeFromNib
    0.50
    antd
    0.47
    йся
    0.47
    Джерела
    0.47
    LOCALE
    0.47
    Activations Density 1.544%

    No Known Activations