© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97398
    Prev
    Next
    INDEX
    Explanations

    fitting, sizes, technical details

    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
    
    -0.95
     BitmapFactory
    -0.83
    expandindo
    -0.77
     שוליים
    -0.76
     leſs
    -0.74
     bezeichneter
    -0.73
     nôtre
    -0.73
     HasFactory
    -0.73
     themſelves
    -0.73
     ſever
    -0.71
    POSITIVE LOGITS
     and
    0.46
    intellij
    0.44
    通りの
    0.34
     Street
    0.33
    oodle
    0.33
    通り
    0.33
    persistence
    0.31
     &
    0.31
     seguido
    0.31
    openConnection
    0.31
    Activations Density 0.000%

    No Known Activations