© 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. 12-RES-MATRYOSHKA-DC
    7. 25900
    Prev
    Next
    INDEX
    Explanations

    specific code-related sequences and expressions in a programming or data context

    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
    Negative Logits
     TabLayout
    -0.50
    StoryboardSegue
    -0.47
    ResumeLayout
    -0.45
    ApiOperation
    -0.45
    籬
    -0.45
    DataAnnotations
    -0.45
    makeText
    -0.44
     MotionEvent
    -0.44
    Tazama
    -0.44
    quelize
    -0.43
    POSITIVE LOGITS
    ("")]
    0.67
    >>()
    0.62
    ')")
    0.59
    Diweddarwch
    0.57
    ).__
    0.57
    جغرافيا
    0.57
    }();
    0.56
    )"),
    0.56
    })()
    0.56
    Hentet
    0.54
    Activations Density 0.067%

    No Known Activations