© 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. 90541
    Prev
    Next
    INDEX
    Explanations

    tead

    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
    tead
    -0.81
    heed
    -0.67
     Poly
    -0.59
     Char
    -0.55
    hauer
    -0.53
    oughlin
    -0.51
    othe
    -0.51
    bari
    -0.51
     undef
    -0.51
    ofsky
    -0.50
    POSITIVE LOGITS
    FieldBuilder
    0.66
     referenties
    0.62
    IsContent
    0.60
    complexContent
    0.56
     TestBed
    0.56
    twimg
    0.55
     oprot
    0.55
    tvguidetime
    0.55
    afficheront
    0.52
    (!__
    0.52
    Activations Density 1.550%

    No Known Activations