© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11676
    Prev
    Next
    INDEX
    Explanations

    and

    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
     retarded
    -0.49
    chequer
    -0.47
     anomalous
    -0.47
    NamedQuery
    -0.46
     pursuance
    -0.45
     retards
    -0.44
     stimulates
    -0.43
    :
    -0.43
     stimul
    -0.42
    Carcinogenicity
    -0.42
    POSITIVE LOGITS
     démocr
    0.89
     réguli
    0.89
     hâte
    0.82
     fermés
    0.82
     fidèles
    0.82
     ouverts
    0.79
     détru
    0.78
     colorés
    0.77
     sauvages
    0.77
     extérieurs
    0.76
    Activations Density 0.025%

    No Known Activations