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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 614
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional experiences and interpersonal connections in narratives

    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
    ”.
    -0.50
    almost
    -0.50
    >().
    -0.50
    casi
    -0.50
    où
    -0.50
     lenker
    -0.49
     almost
    -0.49
    ámos
    -0.48
    ].
    -0.48
    ).
    -0.48
    POSITIVE LOGITS
    的话
    0.82
    的話
    0.78
    ใด
    0.76
     perchance
    0.75
     anything
    0.71
     varsa
    0.71
     any
    0.67
    anything
    0.67
     вдруг
    0.65
     misalnya
    0.64
    Activations Density 1.367%

    No Known Activations