© 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. 10931
    Prev
    Next
    INDEX
    Explanations

    references to ink and inkjet technologies

    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
    Parcelize
    -0.62
    %")
    -0.61
    "%(
    -0.60
    }$}
    -0.57
    ıld
    -0.56
    ###########
    -0.54
    XXXXX
    -0.54
    renia
    -0.54
     SIR
    -0.52
    adors
    -0.52
    POSITIVE LOGITS
     Ink
    1.63
     ink
    1.55
    Ink
    1.40
     inks
    1.38
     Inks
    1.29
     tinta
    1.08
     inkjet
    1.06
     inked
    0.99
    LEncoder
    0.98
    tinta
    0.98
    Activations Density 0.003%

    No Known Activations