© 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. 38621
    Prev
    Next
    INDEX
    Explanations

    descriptive text

    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
     fryer
    -0.52
    $}}
    -0.51
    JspWriter
    -0.51
    ophil
    -0.50
    Datuak
    -0.49
     Secrets
    -0.49
     eski
    -0.48
     booth
    -0.47
    之所以
    -0.47
     crease
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.72
    ValueStyle
    0.72
    TagMode
    0.58
    IndentedString
    0.58
     kasarigan
    0.56
     trees
    0.56
    numerusform
    0.54
     Biôgrafia
    0.54
     horses
    0.53
     alberi
    0.52
    Activations Density 0.060%

    No Known Activations