© 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. 12-RES-MATRYOSHKA-DC
    7. 11953
    Prev
    Next
    INDEX
    Explanations

    separators and formatting indicators in code or markup language

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yty
    -0.58
    tí
    -0.57
     judiciales
    -0.56
     оригіналу
    -0.56
    )});
    -0.51
    }`).
    -0.50
    }?>
    -0.50
    Tämä
    -0.49
     дописавши
    -0.48
     Meksiku
    -0.48
    POSITIVE LOGITS
     BoxFit
    0.79
     مشين
    0.71
    存于互联网档案馆
    0.70
    GEBURTS
    0.67
     StatelessWidget
    0.66
    >
    0.66
    extAlignment
    0.66
     Ababa
    0.65
    urtstag
    0.63
    ἶ
    0.62
    Activations Density 0.008%

    No Known Activations