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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 35
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating actions or directives

    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
    Switcher
    -0.76
    jetbrains
    -0.72
     gethan
    -0.70
     sonne
    -0.68
     Florentine
    -0.68
     fubject
    -0.67
     Shakspeare
    -0.67
    fisher
    -0.66
     NDEBUG
    -0.65
     scattata
    -0.65
    POSITIVE LOGITS
     to
    1.58
     TO
    1.17
     To
    1.08
     be
    0.98
     να
    0.97
    To
    0.96
     make
    0.94
     zu
    0.91
    to
    0.88
    yto
    0.87
    Activations Density 2.480%

    No Known Activations