© 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. 1193
    Prev
    Next
    INDEX
    Explanations

    pros and cons

    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
    TypedDataSet
    -0.78
    PerformLayout
    -0.51
    comings
    -0.49
    RTEX
    -0.49
     שוליים
    -0.49
    ranks
    -0.47
    UnknownFields
    -0.47
    Ranks
    -0.47
    ternut
    -0.47
    étricas
    -0.46
    POSITIVE LOGITS
     of
    0.77
    Portail
    0.62
     endwhile
    0.59
    Personendaten
    0.59
    featureID
    0.54
     saling
    0.52
     NavController
    0.52
    }}],
    0.52
    uidado
    0.52
     Kommune
    0.51
    Activations Density 0.005%

    No Known Activations