Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 32653
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court standing and the mootness of claims

    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
     Theſe
    -0.95
     Majefty
    -0.82
     houſe
    -0.82
     Jefus
    -0.80
     myſelf
    -0.80
     diſt
    -0.80
     itſelf
    -0.79
     uſed
    -0.79
     étoient
    -0.79
     avoient
    -0.78
    POSITIVE LOGITS
     ple
    0.53
     individual
    0.52
     moot
    0.49
     case
    0.47
     v
    0.47
    ReadByte
    0.47
     moo
    0.47
    case
    0.43
    vician
    0.43
     pels
    0.43
    Activations Density 0.003%

    No Known Activations