© 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. 15510
    Prev
    Next
    INDEX
    Explanations

    contextual references to legal proceedings and their outcomes

    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
    dis
    -0.63
    zusch
    -0.59
     परि
    -0.54
     normally
    -0.52
     Dö
    -0.52
    is
    -0.51
    des
    -0.50
    de
    -0.50
     pää
    -0.50
    tris
    -0.49
    POSITIVE LOGITS
    دانشنامهٔ
    1.04
     виправивши
    1.02
    Vidite
    0.93
     препратки
    0.93
    StoryboardSegue
    0.93
     CWE
    0.90
     calendriers
    0.89
    GOTREF
    0.89
     betweenstory
    0.85
     Roskov
    0.85
    Activations Density 0.011%

    No Known Activations