Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 9107
    Prev
    Next
    INDEX
    Explanations

    words related to animals, particularly household pets

    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
    openSession
    -0.50
     come
    -0.47
     
    -0.47
     what
    -0.45
     boys
    -0.45
     Mo
    -0.44
     Su
    -0.43
    FontOfSize
    -0.43
    рта
    -0.42
    "@
    -0.42
    POSITIVE LOGITS
     Majefty
    1.00
     itſelf
    0.94
    ſelf
    0.92
     ―――――
    0.90
     myſelf
    0.86
    ſelves
    0.85
     themſelves
    0.82
     Theſe
    0.79
     Jefus
    0.77
    tagHelperRunner
    0.76
    Activations Density 0.034%

    No Known Activations