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. 23125
    Prev
    Next
    INDEX
    Explanations

    background color or style definitions in code

    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
    ajuato
    -0.81
     --------
    -0.81
    tabria
    -0.77
    =""/>
    -0.76
    rawDesc
    -0.76
    -------
    -0.75
    multer
    -0.75
    subsubsection
    -0.74
     שוליים
    -0.74
    rowad
    -0.72
    POSITIVE LOGITS
     BG
    1.46
    BG
    1.13
     bg
    1.11
    bg
    0.99
    ageo
    0.80
    Bg
    0.79
     Nadia
    0.79
     Bowling
    0.73
    redientes
    0.73
     shalt
    0.72
    Activations Density 0.003%

    No Known Activations