© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97117
    Prev
    Next
    INDEX
    Explanations

    describing physical attributes

    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
     चीज़ों
    -0.66
    CompleteListener
    -0.62
     communiquez
    -0.54
     goutte
    -0.53
     rêves
    -0.53
     suivie
    -0.53
    masalahan
    -0.52
     Unmarshal
    -0.51
    AndEndTag
    -0.50
     scolas
    -0.49
    POSITIVE LOGITS
     men
    0.71
     figures
    0.65
     Normdatei
    0.60
     تضيفلها
    0.59
     manne
    0.57
     women
    0.54
     boys
    0.54
     horsemen
    0.54
     незавершена
    0.54
     man
    0.53
    Activations Density 0.002%

    No Known Activations