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. 16440
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to evidence and convictions

    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
    ArgsConstructor
    -0.84
     समीक्षक
    -0.77
    SBATCH
    -0.71
     Савезне
    -0.69
    TagMode
    -0.68
    ScopeManager
    -0.68
     pamamagitan
    -0.67
    numerusform
    -0.66
    Portály
    -0.65
     resourceCulture
    -0.65
    POSITIVE LOGITS
    <eos>
    0.49
    TAGS
    0.47
     skai
    0.46
     giornal
    0.44
    îné
    0.43
    ↵↵
    0.43
    PP
    0.43
    lement
    0.41
    บบ
    0.41
    њу
    0.40
    Activations Density 0.095%

    No Known Activations