© 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. 19931
    Prev
    Next
    INDEX
    Explanations

    structured programming syntax and control flow statements

    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
    "}"
    -0.78
    endforeach
    -0.76
    "}")
    -0.72
    })*/
    -0.68
    bbene
    -0.67
     arcilla
    -0.67
     {*}
    -0.67
    conium
    -0.67
    पया
    -0.66
    帖最后由
    -0.66
    POSITIVE LOGITS
     CreateTagHelper
    0.88
    DataAnnotations
    0.73
     transfieras
    0.65
     doInBackground
    0.57
     GoogleFonts
    0.57
     Roskov
    0.53
    ffffffff
    0.52
     ProtoMessage
    0.52
    McKin
    0.52
    Dante
    0.51
    Activations Density 0.020%

    No Known Activations