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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16108
    Prev
    Next
    INDEX
    Explanations

    common expressions and phrases related to questioning and reflection

    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
    RegistryLite
    -0.74
    ftagPool
    -0.60
     jsPsych
    -0.53
    SourceChecksum
    -0.52
    skjaer
    -0.51
    :✨
    -0.50
    NewUrlParser
    -0.50
    Життєпис
    -0.49
    SharedCtor
    -0.49
    Распо
    -0.48
    POSITIVE LOGITS
    GMENT
    0.57
    Saludos
    0.56
    destroyAll
    0.55
    XmlAccessType
    0.54
    Enllaces
    0.54
    </table>
    0.53
    stateProvider
    0.52
    routeProvider
    0.52
     pageContext
    0.50
    ご了承ください
    0.50
    Activations Density 0.183%

    No Known Activations