© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19210
    Prev
    Next
    INDEX
    Explanations

    references to security measures, such as locks and safes involving the concealment of items

    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
    iburg
    -0.57
     getchar
    -0.56
     facilities
    -0.54
     jabón
    -0.54
     mote
    -0.54
     terraces
    -0.52
     flott
    -0.50
     lät
    -0.50
     facility
    -0.49
    vermectin
    -0.48
    POSITIVE LOGITS
    Hochspringen
    0.77
     suitcases
    0.68
    AddHtmlAttribute
    0.66
    `;
    0.65
    RetentionPolicy
    0.64
    enumi
    0.63
    godic
    0.63
    erschrank
    0.60
     []:
    0.59
    Rhestr
    0.59
    Activations Density 0.070%

    No Known Activations