© 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. 5-CLT-HP
    7. 91738
    Prev
    Next
    INDEX
    Explanations

    Descriptive/opinionated text

    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
     whereas
    -0.55
     kuten
    -0.54
     with
    -0.52
     vastaan
    -0.50
    RegressionTest
    -0.50
    .
    -0.48
     from
    -0.47
     graça
    -0.46
     terakhir
    -0.45
     sebenarnya
    -0.45
    POSITIVE LOGITS
    StoryboardSegue
    0.70
    kháu
    0.63
     pissed
    0.60
    مقاله
    0.59
    oneofs
    0.58
    WebElementEntity
    0.57
     mama
    0.57
     MIME
    0.56
     momma
    0.55
     tartalomajánló
    0.55
    Activations Density 0.019%

    No Known Activations