© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3996
    Prev
    Next
    INDEX
    Explanations

    elements related to legal arguments and justifications

    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
     Мексичка
    -0.88
     виправивши
    -0.86
    DeleteBehavior
    -0.79
    writeFieldEnd
    -0.79
    دانشنامهٔ
    -0.79
    __':
    -0.78
    __":
    -0.77
    IntoConstraints
    -0.76
    ="#"><
    -0.71
     Meksiku
    -0.69
    POSITIVE LOGITS
     justify
    0.61
     justifies
    0.61
     justification
    0.55
     Justification
    0.55
    justify
    0.52
     justifying
    0.52
     justific
    0.52
     justified
    0.51
    Jus
    0.48
     gius
    0.47
    Activations Density 0.535%

    No Known Activations