© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    phrases concerning meaning, intention, and nuance in language

    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
    StoryboardSegue
    -0.62
     الاطلاع
    -0.59
    IntoConstraints
    -0.59
     समीक्षाएं
    -0.57
    تقاوى
    -0.56
    argout
    -0.56
    ActionCreators
    -0.56
    VersionUID
    -0.55
     Geografia
    -0.54
    oa̍t
    -0.53
    POSITIVE LOGITS
     useRouter
    0.78
    olingo
    0.57
     useHistory
    0.54
     usage
    0.50
     Usage
    0.50
    遣
    0.48
    で使
    0.48
    δά
    0.48
    lex
    0.46
    verbindung
    0.45
    Activations Density 0.526%

    No Known Activations