© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1421
    Prev
    Next
    INDEX
    Explanations

    schools

    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
    RegressionTest
    -0.70
    AutoScaleMode
    -0.68
     nakalista
    -0.62
     Paglinawan
    -0.60
    putan
    -0.57
    complexType
    -0.55
    Vidite
    -0.54
    chehen
    -0.53
    NameInMap
    -0.52
     quis
    -0.51
    POSITIVE LOGITS
     الحره
    0.76
    GeoNames
    0.49
     purpoſe
    0.47
     Algiers
    0.47
    )"),
    0.46
     souten
    0.45
    LEncoder
    0.45
    hø
    0.43
    }$​
    0.43
     Légion
    0.43
    Activations Density 0.003%

    No Known Activations