© 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. 20-CLT-HP
    7. 73751
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · 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
    enderror
    -0.66
    存于互联网档案馆
    -0.62
     Vedi
    -0.60
    ISPR
    -0.57
    lwjgl
    -0.54
     Yew
    -0.54
     ISNI
    -0.54
     propOrder
    -0.54
     Vikipedi
    -0.54
    ylo
    -0.53
    POSITIVE LOGITS
    المشاركات
    0.52
     Sch
    0.50
    ordem
    0.48
    makeConstraints
    0.47
     Black
    0.43
    Referències
    0.43
    ParallelGroup
    0.43
     Central
    0.42
     Bob
    0.42
    ngdoc
    0.42
    Activations Density 0.000%

    No Known Activations