© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 890
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental methodology and practices

    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
    buttonShape
    -0.60
    bonucleic
    -0.59
    fjspx
    -0.56
    >(&
    -0.53
    ρέπει
    -0.53
    zef
    -0.51
    ViewImports
    -0.51
     demás
    -0.50
    клопе
    -0.50
    nościo
    -0.50
    POSITIVE LOGITS
     reality
    0.86
     realities
    0.85
    reality
    0.84
     Reality
    0.83
     actuality
    0.81
    Reality
    0.80
     réalité
    0.79
    実
    0.76
    实际
    0.76
     praktijk
    0.74
    Activations Density 1.321%

    No Known Activations