© 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. 13883
    Prev
    Next
    INDEX
    Explanations

    Economic prices

    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
     of
    -0.46
    her
    -0.45
    ITE
    -0.45
    pak
    -0.44
    rements
    -0.43
    sements
    -0.43
    w
    -0.40
    head
    -0.38
    of
    -0.38
    set
    -0.38
    POSITIVE LOGITS
    ScopeManager
    0.89
    ⓧ
    0.89
     ArrayAdapter
    0.82
     propOrder
    0.81
    SBATCH
    0.81
     <<<<<<<<<<<<<<
    0.80
    !*\
    0.79
     désolés
    0.78
     HttpNotFound
    0.77
    __*/
    0.76
    Activations Density 0.034%

    No Known Activations