© 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. 710
    Prev
    Next
    INDEX
    Explanations

    patients

    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
     Has
    -0.68
     Itself
    -0.61
    twimg
    -0.60
     Via
    -0.60
     Makes
    -0.59
    ™.
    -0.58
    ®.
    -0.58
     Holds
    -0.58
     Through
    -0.57
    LEncoder
    -0.57
    POSITIVE LOGITS
     should
    0.69
    oubliez
    0.52
    ConstraintMaker
    0.47
     inher
    0.46
    ParallelGroup
    0.46
     must
    0.45
     ویکی‌پدیا
    0.45
    eriks
    0.45
    CloseOperation
    0.44
     tend
    0.43
    Activations Density 0.001%

    No Known Activations