© 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. 76680
    Prev
    Next
    INDEX
    Explanations

    fixing/attaching

    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
    setVerticalGroup
    -0.82
     polaire
    -0.67
     nuages
    -0.66
     sélectionné
    -0.65
     traités
    -0.64
     ListTile
    -0.63
     يتيمه
    -0.62
     délé
    -0.61
     vectorielle
    -0.60
     abstrait
    -0.60
    POSITIVE LOGITS
     fixed
    0.79
     screwed
    0.68
     mounted
    0.65
    AsUp
    0.61
     moun
    0.59
     bolted
    0.58
     rigidly
    0.54
    fixed
    0.54
     si
    0.52
    TypedDataSet
    0.52
    Activations Density 0.007%

    No Known Activations