© 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. 5-CLT-HP
    7. 91378
    Prev
    Next
    INDEX
    Explanations

    of

    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
    AnimationsModule
    -0.59
     ویکی‌پدیا
    -0.57
    PerformLayout
    -0.51
    دانشنامهٔ
    -0.49
    awtextra
    -0.48
    UnusedPrivate
    -0.48
     gallop
    -0.47
     aerobic
    -0.46
     NSCoder
    -0.45
     bacteria
    -0.44
    POSITIVE LOGITS
     a
    1.05
     betweenstory
    0.74
     an
    0.71
     the
    0.67
    tsam
    0.58
     Through
    0.54
     Together
    0.54
     Launched
    0.54
    intenant
    0.54
     our
    0.54
    Activations Density 0.009%

    No Known Activations