© 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
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3013
    Prev
    Next
    INDEX
    Explanations

    Delphi code blocks and certain punctuation marks frequently used in that language

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    '}>
    -0.92
    "]}
    -0.84
    ']}
    -0.84
    }');
    -0.81
    }`);
    -0.78
    ()}>
    -0.77
    `}
    -0.76
    }`;
    -0.76
    }>
    -0.75
    ')}
    -0.73
    POSITIVE LOGITS
    end
    0.90
     end
    0.84
    End
    0.71
    END
    0.66
     END
    0.66
     End
    0.63
    else
    0.57
    endal
    0.57
    Enders
    0.57
    URLException
    0.56
    Activations Density 0.097%

    No Known Activations