© 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. 12284
    Prev
    Next
    INDEX
    Explanations

    occurrences of code-related entities, particularly focusing on data structures and method definitions

    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
     themselves
    -0.57
     those
    -0.53
    Memento
    -0.51
     simili
    -0.50
     these
    -0.49
     những
    -0.48
     key
    -0.47
     majeur
    -0.47
     alike
    -0.47
    ágok
    -0.47
    POSITIVE LOGITS
     للاسماء
    0.93
     nakalista
    0.91
    RegistryLite
    0.91
    ">//
    0.88
    LookAnd
    0.82
    SourceChecksum
    0.79
     ويكيپيديا
    0.77
    >{@
    0.77
    EndGlobalSection
    0.75
    󠁮
    0.75
    Activations Density 0.190%

    No Known Activations