© 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. 1767
    Prev
    Next
    INDEX
    Explanations

    repeated numerical patterns or sequences

    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
    IsMutable
    -0.98
     myſelf
    -0.95
     uſed
    -0.93
     raiſ
    -0.91
     chofe
    -0.89
     themſelves
    -0.88
     ſtill
    -0.88
     pleaſure
    -0.88
     ſtate
    -0.88
     purpoſe
    -0.88
    POSITIVE LOGITS
    gefügt
    0.51
    Preliminary
    0.48
     be
    0.48
    mo
    0.47
    <sup>
    0.47
    roc
    0.47
    tabular
    0.46
    >);
    0.46
     Hau
    0.45
    %%%%%%%%%%%%%%%%
    0.45
    Activations Density 0.704%

    No Known Activations