© 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. 5790
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or expressions of distress

    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
    -
    -0.76
     vícti
    -0.69
     verticale
    -0.58
     Westchester
    -0.57
     starlight
    -0.57
     Rhine
    -0.56
    NegativeButton
    -0.55
     anteriore
    -0.54
     montanha
    -0.54
    भी
    -0.54
    POSITIVE LOGITS
    verständlich
    0.80
     ujednoznacz
    0.73
    !',
    0.71
    setCellValue
    0.69
    sizeCache
    0.69
    ".
    0.68
    LookAnd
    0.68
    }">
    0.67
    دانشنامهٔ
    0.66
    ?',
    0.66
    Activations Density 0.227%

    No Known Activations