© 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. 1-CLT-HP
    7. 8816
    Prev
    Next
    INDEX
    Explanations

    -er

    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
    soort
    -0.50
    Invariant
    -0.46
     quedado
    -0.41
    Lepid
    -0.40
    ISupport
    -0.40
    endpush
    -0.39
     independencia
    -0.39
     carrinho
    -0.37
     gustado
    -0.37
    umus
    -0.37
    POSITIVE LOGITS
    SequentialGroup
    0.79
    Personensuche
    0.69
     ExecuteAsync
    0.65
     препратки
    0.64
     chi̍t
    0.63
    entile
    0.63
    WindowConstants
    0.63
    __*/
    0.61
    ádza
    0.60
    \{\\
    0.59
    Activations Density 0.041%

    No Known Activations