© 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. 1-RES-MATRYOSHKA-DC
    7. 173
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical measures such as standard deviation and descriptions of experimental data quality

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritsar
    -0.68
    Eksterne
    -0.66
     vanskelig
    -0.65
    </table>
    -0.65
    HasColumnName
    -0.64
     Ashraf
    -0.63
     synap
    -0.63
    strptime
    -0.63
    tritte
    -0.63
    bebasan
    -0.63
    POSITIVE LOGITS
     SD
    1.39
    sd
    1.30
    md
    1.27
    MD
    1.23
    td
    1.22
    cd
    1.22
    SD
    1.20
     Cod
    1.20
     PED
    1.20
     PD
    1.18
    Activations Density 4.097%

    No Known Activations