© 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. 0-CLT-HP
    7. 43184
    Prev
    Next
    INDEX
    Explanations

    announcements

    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
    bootstrapcdn
    -0.71
    rrggbb
    -0.69
    abetes
    -0.66
     européennes
    -0.65
     gedachten
    -0.61
     voici
    -0.60
    łyn
    -0.60
    elee
    -0.59
    gelopen
    -0.59
     ogóle
    -0.58
    POSITIVE LOGITS
     a
    0.87
    <bos>
    0.80
     the
    0.77
     five
    0.75
     six
    0.69
     two
    0.69
     seven
    0.67
     four
    0.66
     several
    0.66
     an
    0.65
    Activations Density 0.105%

    No Known Activations