© 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. 90834
    Prev
    Next
    INDEX
    Explanations

    dynamically

    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
     autorytatywna
    -0.76
    uxxxx
    -0.75
    FunctionFlags
    -0.75
     automatiques
    -0.66
     fraî
    -0.64
     réguli
    -0.64
    XmlAccessType
    -0.63
     nécessairement
    -0.63
     aveug
    -0.63
     automatiquement
    -0.62
    POSITIVE LOGITS
     change
    0.60
     set
    0.58
     discover
    0.55
    StoryboardSegue
    0.55
     sets
    0.54
     discovery
    0.51
     adjust
    0.48
     assign
    0.48
     SET
    0.48
     discovering
    0.48
    Activations Density 0.005%

    No Known Activations