© 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. 77724
    Prev
    Next
    INDEX
    Explanations

    Code and technical snippets

    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
     Faça
    -0.64
     isNameExpr
    -0.60
     fevere
    -0.60
     Anſ
    -0.60
     doth
    -0.59
     Connectez
    -0.58
     Hace
    -0.58
    ineno
    -0.57
     Diſ
    -0.56
    Knowing
    -0.56
    POSITIVE LOGITS
     you
    0.60
     in
    0.57
    PerformLayout
    0.56
    EReference
    0.53
     on
    0.52
    tokine
    0.51
     inside
    0.50
    ]--;
    0.47
     out
    0.47
     we
    0.47
    Activations Density 0.001%

    No Known Activations