© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    references to specific jurisdictions or legal cases related to states, particularly Kansas and Missouri

    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
     دیکھیے
    -0.78
     utafitiHapana
    -0.71
    protoimpl
    -0.69
     سكانية
    -0.68
    (!__
    -0.66
     &___
    -0.60
    蜒
    -0.59
    XmlRootElement
    -0.58
    újo
    -0.58
     fidélité
    -0.58
    POSITIVE LOGITS
    enumi
    0.55
     onCreateView
    0.53
     Serap
    0.47
     kiti
    0.47
    addGroup
    0.47
    nages
    0.47
    orElse
    0.47
     dressing
    0.46
     concentrated
    0.46
    アクセ
    0.44
    Activations Density 0.008%

    No Known Activations