© 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. 10505
    Prev
    Next
    INDEX
    Explanations

    learning, cancer

    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
     enfans
    -0.77
     avoient
    -0.77
    NameInMap
    -0.75
     tartalomajánló
    -0.74
     ouvriers
    -0.69
     Numerade
    -0.69
    AccessorTable
    -0.68
     juges
    -0.67
    Geplaatst
    -0.66
     $_"
    -0.66
    POSITIVE LOGITS
     of
    0.57
     in
    0.55
     is
    0.53
    cheron
    0.49
     was
    0.49
    MessageDigest
    0.49
    ProgressHUD
    0.45
     and
    0.45
     returns
    0.45
    addObject
    0.45
    Activations Density 0.063%

    No Known Activations