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. 24701
    Prev
    Next
    INDEX
    Explanations

    references to rights or legal entitlements

    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
    ]$}
    -0.78
    </table>
    -0.75
    akterysty
    -0.74
     right
    -0.73
    FieldNumber
    -0.71
     PopupWindow
    -0.71
    ropriate
    -0.69
    perature
    -0.68
     Bacteriol
    -0.68
     drap
    -0.68
    POSITIVE LOGITS
     Rights
    0.73
    unknownFields
    0.66
     متعلقه
    0.65
    Rights
    0.64
    čené
    0.64
     RIGHTS
    0.63
    URIComponent
    0.63
    hintText
    0.63
    aarrggbb
    0.62
     rights
    0.60
    Activations Density 0.010%

    No Known Activations