© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14521
    Prev
    Next
    INDEX
    Explanations

    article

    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
    lojik
    -0.50
     vuoden
    -0.50
     vastaan
    -0.49
    TypeOf
    -0.48
    blog
    -0.48
     mechanistic
    -0.47
    pretation
    -0.47
     cotone
    -0.46
     mosso
    -0.46
     dư
    -0.46
    POSITIVE LOGITS
    <bos>
    0.75
    sizeCache
    0.66
     CreateTagHelper
    0.60
    ✨:
    0.59
    eradish
    0.57
    IntoConstraints
    0.57
     Mérimée
    0.57
    ertale
    0.56
    makeText
    0.55
    issauga
    0.55
    Activations Density 0.013%

    No Known Activations