© 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. 15502
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or strong assertions 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
    migrationBuilder
    -0.93
     سكانية
    -0.91
    
    -0.91
    UrlResolution
    -0.87
    Portail
    -0.85
     kasarigan
    -0.85
     Signalez
    -0.85
     الحره
    -0.84
    ="/">
    -0.79
    })*/
    -0.79
    POSITIVE LOGITS
    lover
    0.43
    Gew
    0.41
    iedz
    0.41
    wayat
    0.41
    LAYER
    0.41
     att
    0.41
    auteuil
    0.40
    lioz
    0.40
     love
    0.40
    pian
    0.40
    Activations Density 0.010%

    No Known Activations