© 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. 24579
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to legal cases or individuals involved in legal contexts

    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
    arks
    -0.46
    fier
    -0.41
     réponse
    -0.41
     vérité
    -0.41
     incapa
    -0.40
     рубе
    -0.39
    Turno
    -0.39
     Skinner
    -0.38
    getSystemService
    -0.38
    󠁴
    -0.38
    POSITIVE LOGITS
     мәкал
    0.90
    脚注の使い方
    0.90
    StructEnd
    0.89
     himo
    0.83
    #+#
    0.82
     SEDS
    0.77
     kasarigan
    0.76
     متعلقه
    0.75
     समीक्षक
    0.74
     مشين
    0.71
    Activations Density 0.002%

    No Known Activations