© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13355
    Prev
    Next
    INDEX
    Explanations

    downstream or upstream

    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
    rungsseite
    -0.90
     upstream
    -0.87
     downstream
    -0.86
    upstream
    -0.75
    Upstream
    -0.68
     upstairs
    -0.65
    interopRequire
    -0.63
     Upstream
    -0.62
    jsonwebtoken
    -0.61
     downstairs
    -0.59
    POSITIVE LOGITS
    s
    0.62
    SaveChangesAsync
    0.53
    AlterField
    0.50
    saf
    0.49
     cipolla
    0.49
    adə
    0.47
     megsz
    0.47
     magique
    0.46
    nodoc
    0.46
     battu
    0.46
    Activations Density 0.014%

    No Known Activations