© 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. 1-CLT-HP
    7. 15281
    Prev
    Next
    INDEX
    Explanations

    and

    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
    /
    -0.65
     other
    -0.54
     has
    -0.51
     subsequent
    -0.50
    }();
    -0.50
     subsequently
    -0.49
     is
    -0.47
     may
    -0.47
     ensures
    -0.46
    +)/
    -0.46
    POSITIVE LOGITS
    iotensin
    0.70
    ResumeLayout
    0.70
     الدولى
    0.69
     définiti
    0.66
     nôtre
    0.65
    存于互联网档案馆
    0.63
    Geplaatst
    0.62
     Numerade
    0.62
    endregion
    0.61
    pergillus
    0.60
    Activations Density 0.447%

    No Known Activations