© 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. 0-CLT-HP
    7. 42542
    Prev
    Next
    INDEX
    Explanations

    regenerate

    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
     regenerate
    -1.24
     regeneration
    -1.12
     regener
    -1.10
     regenerated
    -1.05
    MLLoader
    -1.01
     photolibrary
    -0.99
    ial
    -0.98
     Regeneration
    -0.92
     disambiguazione
    -0.92
     كومونز
    -0.91
    POSITIVE LOGITS
    i
    0.69
    a
    0.54
    e
    0.46
     could
    0.45
    ي
    0.44
    </em>
    0.43
    ...
    0.42
    n
    0.41
    iv
    0.41
     måtte
    0.41
    Activations Density 0.102%

    No Known Activations