© 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. 770
    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
     GenerationType
    -0.90
    IUrlHelper
    -0.86
    AutoScaleMode
    -0.81
    )_/¯
    -0.79
     utafitiHapana
    -0.77
    AsUp
    -0.73
    UnusedPrivate
    -0.72
     дописавши
    -0.71
    Clik
    -0.70
     '\\;'
    -0.70
    POSITIVE LOGITS
    Dequeue
    0.59
    vore
    0.51
    幡
    0.47
    allos
    0.46
    ich
    0.45
    anta
    0.45
    documentElement
    0.45
    </em>
    0.44
    []
    0.43
    .$,
    0.42
    Activations Density 0.007%

    No Known Activations