© 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. 4-CLT-HP
    7. 589
    Prev
    Next
    INDEX
    Explanations

    come

    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
     الحره
    -0.72
     nakalista
    -0.68
    ContextHolder
    -0.68
    httphttps
    -0.66
     CURIAM
    -0.65
     متعلقه
    -0.62
    Geplaatst
    -0.61
    tadır
    -0.60
     come
    -0.59
    Portale
    -0.59
    POSITIVE LOGITS
    avec
    0.71
     with
    0.62
     avec
    0.59
    enschaft
    0.54
    Along
    0.51
    with
    0.50
    along
    0.50
     μαζί
    0.49
    With
    0.48
     við
    0.47
    Activations Density 0.003%

    No Known Activations