© 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. 5-CLT-HP
    7. 4563
    Prev
    Next
    INDEX
    Explanations

    inventions

    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
     ainfi
    -1.05
     auffi
    -1.02
     purpoſe
    -0.95
     ſtate
    -0.89
     houſe
    -0.87
     étoient
    -0.86
     feroit
    -0.85
     iſt
    -0.84
     avoient
    -0.83
     plufieurs
    -0.82
    POSITIVE LOGITS
     about
    0.64
     and
    0.59
    ,
    0.59
    -
    0.54
    addPreferredGap
    0.51
     all
    0.50
     &
    0.50
     telling
    0.50
     (
    0.49
     on
    0.49
    Activations Density 0.021%

    No Known Activations