© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 10469
    Prev
    Next
    INDEX
    Explanations

    references to a specific Italian-related film or entity

    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
    Negative Logits
    }-\
    -0.66
    }+\
    -0.65
    )-\
    -0.65
    Datuak
    -0.61
    expandindo
    -0.57
    )+\
    -0.56
    ito
    -0.55
     bParam
    -0.53
     doInBackground
    -0.53
    Portail
    -0.52
    POSITIVE LOGITS
    ita
    1.75
    ITA
    1.31
    Попис
    0.66
    ustimmung
    0.65
    )=\
    0.65
    )}=\
    0.65
    tinta
    0.60
     AppBundle
    0.60
    }}=\
    0.59
    Brainz
    0.59
    Activations Density 0.001%

    No Known Activations