© 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. 24669
    Prev
    Next
    INDEX
    Explanations

    control flow statements, particularly breaks and ends of blocks

    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
     houſe
    -0.61
    abro
    -0.60
     pleaſure
    -0.60
    atically
    -0.59
     kanssa
    -0.59
    )•
    -0.59
     mergeFrom
    -0.58
     bParam
    -0.58
     PLW
    -0.56
     bahawa
    -0.56
    POSITIVE LOGITS
    Koordinaten
    0.75
    else
    0.71
    rungsseite
    0.70
    elif
    0.67
     else
    0.65
    ory
    0.62
    LookAnd
    0.62
    BufferException
    0.58
     glyphicon
    0.57
    buz
    0.56
    Activations Density 0.009%

    No Known Activations