© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    terms related to comparative analysis and differentiation of traits

    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
     sat
    -0.48
     Insel
    -0.41
     Mere
    -0.40
    सत
    -0.40
    сован
    -0.39
    Mere
    -0.39
    strdup
    -0.39
    ponte
    -0.39
     Hi
    -0.38
    voo
    -0.38
    POSITIVE LOGITS
    RenderAtEndOf
    1.06
     betweenstory
    0.96
     صوتيه
    0.95
    StoryboardSegue
    0.94
    webElementXpaths
    0.86
    fjspx
    0.83
     FetchType
    0.82
     different
    0.81
     himo
    0.80
    WebServlet
    0.79
    Activations Density 0.093%

    No Known Activations