© 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. 43142
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    })),
    -0.66
     fieldNum
    -0.60
    idhi
    -0.57
     fermés
    -0.55
    ))),
    -0.53
     fréquence
    -0.52
    ')(
    -0.52
    StructEnd
    -0.51
    (')
    -0.51
     évé
    -0.51
    POSITIVE LOGITS
    CGRectMake
    0.60
    gatsby
    0.59
    MigrationBuilder
    0.57
    omock
    0.55
    tanleria
    0.54
    IntoConstraints
    0.54
    URLConnection
    0.52
     ujednoznacz
    0.51
     pylint
    0.50
    rzost
    0.50
    Activations Density 0.228%

    No Known Activations