© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8935
    Prev
    Next
    INDEX
    Explanations

    academics and learning

    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
     gynhyrchwyd
    -0.73
     oprot
    -0.60
    orsese
    -0.59
     Theſe
    -0.59
    ciech
    -0.58
    ^(@)
    -0.58
    '},
    -0.57
    données
    -0.56
     Byzantium
    -0.56
     Vaj
    -0.54
    POSITIVE LOGITS
    flage
    0.50
    ary
    0.49
    eap
    0.45
     Coe
    0.44
    EventQueue
    0.44
    onium
    0.43
    ians
    0.43
    antro
    0.42
     tengas
    0.42
    ables
    0.42
    Activations Density 0.011%

    No Known Activations