© 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. 40128
    Prev
    Next
    INDEX
    Explanations

    hematopoietic

    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
     démocr
    -0.83
    IntoConstraints
    -0.79
     avoient
    -0.76
     mères
    -0.75
     Wicidata
    -0.74
     étoient
    -0.73
     rayures
    -0.73
     réguli
    -0.73
    berdayakan
    -0.72
    DockStyle
    -0.71
    POSITIVE LOGITS
    <bos>
    0.83
    ization
    0.74
    ized
    0.64
    izing
    0.64
    batore
    0.61
    ise
    0.57
    ised
    0.54
    ists
    0.52
    ities
    0.52
    ize
    0.51
    Activations Density 0.103%

    No Known Activations