© 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. 3715
    Prev
    Next
    INDEX
    Explanations

    phrases that express purpose or intention

    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
     pleaſure
    -0.58
    ыгана
    -0.54
    guilty
    -0.54
    WEBPACK
    -0.53
     écoles
    -0.53
    ětí
    -0.53
     Pringle
    -0.52
    ricanes
    -0.52
     Perseverance
    -0.51
    LEncoder
    -0.51
    POSITIVE LOGITS
    VideoCapture
    0.76
    jooq
    0.73
    IContainer
    0.72
    TintMode
    0.67
     propOrder
    0.65
    colgroup
    0.63
     sodass
    0.63
    antMatchers
    0.63
    ponses
    0.60
     getItemId
    0.60
    Activations Density 0.113%

    No Known Activations