© 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. 0-CLT-HP
    7. 95720
    Prev
    Next
    INDEX
    Explanations

    i

    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
    ReusableCell
    -0.60
    EndContext
    -0.57
     <<<<<<<<<<<<<<
    -0.57
     "$@"
    -0.56
    oneofs
    -0.55
     transpired
    -0.52
    OfWork
    -0.51
    \{\\
    -0.51
     perished
    -0.51
    WSGI
    -0.51
    POSITIVE LOGITS
    <bos>
    0.71
    Geografía
    0.66
     the
    0.63
    Šaltiniai
    0.55
     domestiques
    0.52
    VIEWS
    0.49
    abstractmethod
    0.49
    thof
    0.48
    ANEOUS
    0.47
     تانيه
    0.46
    Activations Density 0.081%

    No Known Activations