© 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. 5687
    Prev
    Next
    INDEX
    Explanations

    expressions of physical sensations and emotions

    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
     myſelf
    -0.92
     Tartar
    -0.87
     Monfieur
    -0.86
    martre
    -0.86
     Stow
    -0.85
     depositphotos
    -0.83
     Caspian
    -0.82
     Cientí
    -0.81
     photolibrary
    -0.81
     Duma
    -0.81
    POSITIVE LOGITS
     felt
    1.31
     Feel
    1.17
     feel
    1.16
    Feels
    1.13
     feels
    1.13
    Feel
    1.11
     feeling
    1.09
    Felt
    1.09
     Feels
    1.08
     FEEL
    1.03
    Activations Density 0.045%

    No Known Activations