© 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. 10546
    Prev
    Next
    INDEX
    Explanations

    if

    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
     a
    -0.50
     Nitrogen
    -0.49
    UrlResolution
    -0.48
     serum
    -0.47
     EventArgs
    -0.47
    oredCriteria
    -0.46
     HasFactory
    -0.46
    Naissance
    -0.45
     Downing
    -0.45
     Allí
    -0.45
    POSITIVE LOGITS
     arşivlendi
    0.61
     $|
    0.57
    iastes
    0.55
    orphism
    0.51
    Galer
    0.50
     &___
    0.50
    StoreMessageInfo
    0.49
     $\|
    0.49
    duate
    0.47
     segredo
    0.46
    Activations Density 0.041%

    No Known Activations