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. 26712
    Prev
    Next
    INDEX
    Explanations

    references to GitHubusercontent, which indicates content hosted on GitHub's raw file service

    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
    évaluateur
    -0.80
     '').
    -0.65
    Diweddarwch
    -0.56
    ungkap
    -0.51
     "").
    -0.51
    stanford
    -0.51
    nina
    -0.49
    Expedia
    -0.48
     gyhoeddwyd
    -0.48
     Hajj
    -0.47
    POSITIVE LOGITS
    usercontent
    5.56
     оригіналу
    0.86
    antMatchers
    0.85
     BoxFit
    0.80
    AndEndTag
    0.73
    IsContent
    0.72
    sendRedirect
    0.71
     محفوظة
    0.67
    FilterChain
    0.67
    ImageContext
    0.66
    Activations Density 0.004%

    No Known Activations