© 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. 3558
    Prev
    Next
    INDEX
    Explanations

    terms related to specific terminology and patterns in scientific and legal texts

    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
    contentLoaded
    -1.03
    ьаж
    -1.00
    Tikang
    -0.98
    комму
    -0.94
    IndentedString
    -0.94
    ihnachten
    -0.90
    ogeneity
    -0.89
    RTDA
    -0.89
    EndGlobalSection
    -0.88
     Benth
    -0.86
    POSITIVE LOGITS
    ar
    1.30
    er
    1.22
    lar
    1.11
    AR
    1.10
     Qar
    0.98
     Yar
    0.91
    CAR
    0.90
    ara
    0.89
    har
    0.89
     yar
    0.88
    Activations Density 0.569%

    No Known Activations