© 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. 0-CLT-HP
    7. 42256
    Prev
    Next
    INDEX
    Explanations

    distinguishing/defining

    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
     CURIAM
    -0.73
    ########.
    -0.72
     utafitiHapana
    -0.63
     differentiates
    -0.63
     distinguishes
    -0.60
    GraphicsUnit
    -0.59
    ]")]
    -0.57
    ifferentiated
    -0.57
     '\\;'
    -0.56
    onomic
    -0.55
    POSITIVE LOGITS
    CAPTION
    0.59
    lenir
    0.57
    LookAnd
    0.55
    FieldNumber
    0.54
     }}$}
    0.54
    </caption>
    0.53
    dostęp
    0.51
    akaian
    0.51
     zostać
    0.51
     Arxivat
    0.50
    Activations Density 0.032%

    No Known Activations