Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74370
    Prev
    Next
    INDEX
    Explanations

    body parts

    np_max-act-logits · 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
     étions
    -0.63
     étoient
    -0.63
    ']==
    -0.62
     Majefty
    -0.62
    ])):
    -0.60
     avoient
    -0.59
     prochaines
    -0.58
    astify
    -0.57
    setVerticalGroup
    -0.56
    ✨:
    -0.55
    POSITIVE LOGITS
     spine
    0.68
     spinal
    0.60
     eye
    0.59
     vision
    0.57
     back
    0.57
     heart
    0.54
     Back
    0.54
     eyes
    0.54
     head
    0.52
    skull
    0.52
    Activations Density 0.006%

    No Known Activations