© 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. 16655
    Prev
    Next
    INDEX
    Explanations

    commas in 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
    GEBURTSDATUM
    -0.98
    SequentialGroup
    -0.86
    HomeAsUpEnabled
    -0.85
     Roskov
    -0.81
    ThroughAttribute
    -0.79
    awtextra
    -0.79
    SharedCtor
    -0.78
     NSCoder
    -0.78
    StoryboardSegue
    -0.77
     Signalez
    -0.77
    POSITIVE LOGITS
    kegaard
    0.60
    magini
    0.50
     trotzdem
    0.50
    ayak
    0.49
    ripto
    0.49
    PubMed
    0.48
     citoy
    0.47
     pareil
    0.47
     russes
    0.47
     polaire
    0.47
    Activations Density 0.025%

    No Known Activations