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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1517
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize personal responsibility and individual choice

    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
    TagHelper
    -0.71
    ValueStyle
    -0.60
    multirow
    -0.50
    LabelTagHelper
    -0.48
    Демографія
    -0.48
    pushFollow
    -0.46
    τα
    -0.46
    findViewById
    -0.44
    icom
    -0.44
    AddTagHelper
    -0.44
    POSITIVE LOGITS
     discretion
    0.75
     decide
    0.74
     independently
    0.72
     entscheiden
    0.70
    decide
    0.69
     librement
    0.68
     subjective
    0.68
    ArgsConstructor
    0.67
     zelf
    0.66
     decides
    0.66
    Activations Density 1.118%

    No Known Activations