© 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. 21436
    Prev
    Next
    INDEX
    Explanations

    image file references in a document

    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
     Fortun
    -0.63
    võ
    -0.61
     excise
    -0.61
    ER
    -0.60
     Palla
    -0.60
    er
    -0.59
    bade
    -0.59
     bla
    -0.58
     kore
    -0.57
    ث
    -0.57
    POSITIVE LOGITS
    jpg
    1.76
     jpg
    1.13
    JPG
    1.10
     JPG
    1.05
    AndEndTag
    0.99
    transQ
    0.96
     nakalista
    0.95
    [++
    0.90
    JspWriter
    0.90
    expandindo
    0.88
    Activations Density 0.002%

    No Known Activations