© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43501
    Prev
    Next
    INDEX
    Explanations

    ochemistry

    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
     finally
    -0.92
    DeleteBehavior
    -0.92
     חיצוניים
    -0.88
    finally
    -0.87
     enfin
    -0.85
    IntoConstraints
    -0.85
     наконец
    -0.81
     שוליים
    -0.79
     FINALLY
    -0.77
    Filmographie
    -0.77
    POSITIVE LOGITS
    b
    0.47
    l
    0.46
     поми
    0.46
     ab
    0.46
    dev
    0.45
     gr
    0.45
    bes
    0.45
     [*]
    0.44
     vě
    0.43
     posterior
    0.42
    Activations Density 0.115%

    No Known Activations