© 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. 4422
    Prev
    Next
    INDEX
    Explanations

    hydrogen

    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
    dataIndex
    -0.52
    udu
    -0.50
     DOI
    -0.50
     NHL
    -0.50
     al
    -0.48
     Berg
    -0.47
    zeera
    -0.47
    çon
    -0.46
    het
    -0.45
    öm
    -0.45
    POSITIVE LOGITS
    awtextra
    0.85
    клопе
    0.84
     صوتيه
    0.74
     démocr
    0.72
     iprot
    0.71
     videre
    0.70
     étoit
    0.68
    ValueStyle
    0.66
     vidare
    0.66
    يكب
    0.65
    Activations Density 0.002%

    No Known Activations