© 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. 7985
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to functions and series expansions

    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
    ]{\
    -0.67
    '],$
    -0.66
    '].'
    -0.60
     createSlice
    -0.59
     Wied
    -0.57
    tvguidetime
    -0.57
    ])+
    -0.57
    makeText
    -0.56
     '',
    -0.55
    posedge
    -0.54
    POSITIVE LOGITS
     дописавши
    0.87
    TintMode
    0.69
     AssemblyProduct
    0.68
    IntoConstraints
    0.59
     betweenstory
    0.56
    VIAF
    0.54
     MainAxisSize
    0.54
    atility
    0.53
    CloseOperation
    0.53
     Exacts
    0.52
    Activations Density 0.016%

    No Known Activations