© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72111
    Prev
    Next
    INDEX
    Explanations

    bird

    np_max-act-logits · 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
     feathers
    -1.01
     birds
    -0.94
     chicks
    -0.93
     plumage
    -0.88
     bird
    -0.86
     feather
    -0.85
     feathered
    -0.82
     chick
    -0.81
     avian
    -0.77
     flight
    -0.76
    POSITIVE LOGITS
    +#+#
    0.68
     betweenstory
    0.65
    tvguidetime
    0.63
     Dent
    0.61
    PerformLayout
    0.61
    AndEndTag
    0.59
    balleur
    0.58
     Lyons
    0.56
    harap
    0.54
    Dent
    0.53
    Activations Density 0.017%

    No Known Activations