© 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. 21460
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific formatting characteristics in the text

    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
     كومونز
    -0.79
    脚注の使い方
    -0.77
     للمعارف
    -0.67
    TypedDataSet
    -0.66
    Discografia
    -0.65
    AndEndTag
    -0.62
     Molecules
    -0.61
    homonymie
    -0.60
    DebuggerNonUser
    -0.57
     molé
    -0.56
    POSITIVE LOGITS
     nahilalakip
    0.55
     mergeFrom
    0.54
    glUniform
    0.50
    classmethod
    0.48
     onPage
    0.47
     progressBar
    0.46
    }}],
    0.44
     SEDS
    0.44
    +=
    0.44
    ıt
    0.43
    Activations Density 0.000%

    No Known Activations