© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    by/through

    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
    hemiah
    -0.61
     Normdatei
    -0.60
     condizione
    -0.58
    Diwedd
    -0.58
    verwijspagina
    -0.57
    endpush
    -0.56
    Démographie
    -0.56
     varandra
    -0.56
    mbolos
    -0.56
     egyéb
    -0.56
    POSITIVE LOGITS
     providing
    0.62
     relying
    0.61
     making
    0.60
     giving
    0.59
     being
    0.58
     using
    0.57
     offering
    0.54
     killing
    0.52
     getting
    0.52
     including
    0.52
    Activations Density 0.010%

    No Known Activations