© 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. 0-CLT-HP
    7. 97303
    Prev
    Next
    INDEX
    Explanations

    relying

    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
     approach
    -1.64
    approach
    -1.48
     Approach
    -1.45
     approaches
    -1.43
     APPROACH
    -1.42
     approached
    -1.41
    Approach
    -1.37
     approche
    -1.34
     approaching
    -1.22
     Approaches
    -1.20
    POSITIVE LOGITS
     on
    0.79
     upon
    0.68
     to
    0.60
     fond
    0.52
     for
    0.51
    </blockquote>
    0.50
     aux
    0.50
    s
    0.50
    ródło
    0.49
     rest
    0.48
    Activations Density 0.128%

    No Known Activations