© 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. 14013
    Prev
    Next
    INDEX
    Explanations

    HTML or code structure elements

    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
    <caption>
    -0.60
    VEY
    -0.50
    vey
    -0.49
     amor
    -0.48
    .}}
    -0.48
    ])/
    -0.48
    Erf
    -0.47
    ([[
    -0.46
     Mercer
    -0.46
    CrossRef
    -0.46
    POSITIVE LOGITS
     nakalista
    0.84
    setVerticalGroup
    0.82
    DoubleQuotes
    0.78
     GenerationType
    0.77
    +#+#
    0.77
     propOrder
    0.76
    featureID
    0.75
     kasarigan
    0.75
     ivelany
    0.73
     protoimpl
    0.72
    Activations Density 0.000%

    No Known Activations