© 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. 3206
    Prev
    Next
    INDEX
    Explanations

    terms related to features in various contexts

    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
    Alp
    -0.96
     PVA
    -0.94
     Jind
    -0.86
    idp
    -0.85
     CMP
    -0.85
    protoimpl
    -0.84
     pregunto
    -0.84
    ]^{-
    -0.84
    thschild
    -0.83
     photolibrary
    -0.83
    POSITIVE LOGITS
     features
    1.86
     feature
    1.73
     Features
    1.72
    Features
    1.66
    features
    1.62
     FEATURE
    1.61
     Feature
    1.59
    Feature
    1.53
     FEATURES
    1.53
    feature
    1.49
    Activations Density 0.079%

    No Known Activations