© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 76407
    Prev
    Next
    INDEX
    Explanations

    Stop words

    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
     ainfi
    -0.85
     étoit
    -0.84
     themſelves
    -0.83
     auroit
    -0.82
     kasarigan
    -0.82
     étoient
    -0.79
     avoient
    -0.77
    IUrlHelper
    -0.77
     enfans
    -0.77
     myſelf
    -0.76
    POSITIVE LOGITS
     of
    0.60
     in
    0.56
    <bos>
    0.56
     for
    0.54
    ,
    0.53
     and
    0.49
    .
    0.49
    ’
    0.48
     to
    0.48
     from
    0.47
    Activations Density 0.000%

    No Known Activations