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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3525
    Prev
    Next
    INDEX
    Explanations

    Cause and effect

    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
    FormTagHelper
    -0.69
     Audiodateien
    -0.68
     sendiri
    -0.56
     antaranya
    -0.55
     åt
    -0.53
     battre
    -0.52
     czym
    -0.50
     especialmente
    -0.50
     demikian
    -0.50
     stesse
    -0.49
    POSITIVE LOGITS
     the
    1.16
     their
    0.90
     its
    0.88
     our
    0.85
    tagext
    0.69
     your
    0.68
     of
    0.68
     '{@
    0.64
    )";
    0.64
     those
    0.62
    Activations Density 0.002%

    No Known Activations