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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17877
    Prev
    Next
    INDEX
    Explanations

    instances of preformatted text or code snippets

    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
     Cabot
    -0.58
    '`
    -0.56
    ")"
    -0.55
     passagers
    -0.54
    λει
    -0.53
     Kredit
    -0.53
     credito
    -0.50
    "`
    -0.50
    Beschrijving
    -0.49
    vedra
    -0.49
    POSITIVE LOGITS
    pre
    1.00
    GraphicsUnit
    0.85
     doInBackground
    0.78
     linkovi
    0.75
    libft
    0.74
    AndEndTag
    0.74
    PRE
    0.73
    发表于
    0.73
    InvalidProtocol
    0.71
     pre
    0.69
    Activations Density 0.001%

    No Known Activations