© 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. 0-CLT-HP
    7. 44064
    Prev
    Next
    INDEX
    Explanations

    sojourn

    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
    sacrifice
    -0.54
    utia
    -0.50
    Charleston
    -0.50
    tolerant
    -0.48
    :✨
    -0.45
     transition
    -0.43
     shunt
    -0.43
    entance
    -0.43
    fromUtf
    -0.43
    ittarius
    -0.42
    POSITIVE LOGITS
    GraphicsUnit
    0.88
     InputDecoration
    0.74
     BoxFit
    0.70
     récomp
    0.65
     déput
    0.64
     ciebie
    0.64
     pinulongan
    0.63
     politiet
    0.60
    AndEndTag
    0.60
     medlemmer
    0.60
    Activations Density 0.011%

    No Known Activations