© 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. 90757
    Prev
    Next
    INDEX
    Explanations

    fetuses

    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
     pond
    -0.69
     lake
    -0.65
    schaft
    -0.63
     Seeder
    -0.59
     Guys
    -0.57
    SourceChecksum
    -0.57
    TagMode
    -0.55
    swimming
    -0.54
     Lake
    -0.52
    IsMutable
    -0.51
    POSITIVE LOGITS
    stdc
    0.62
     Reſ
    0.60
     platelets
    0.60
    ward
    0.59
     otomatig
    0.59
    tvguidetime
    0.59
     AssemblyCulture
    0.57
    ographic
    0.54
    entrySet
    0.54
    avir
    0.54
    Activations Density 0.346%

    No Known Activations