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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16097
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    InputBorder
    -0.63
     subsoil
    -0.62
     onAnimation
    -0.61
     homecoming
    -0.57
     constitutions
    -0.57
     getLogin
    -0.57
    erals
    -0.56
    Bullets
    -0.56
     Kona
    -0.55
     bursa
    -0.54
    POSITIVE LOGITS
    SpringBootTest
    0.66
    awaiter
    0.65
    帖最后由
    0.58
    +#+
    0.57
    .*")]
    0.57
    principalTable
    0.56
    weile
    0.56
    istoitu
    0.55
     nahilalakip
    0.54
    
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.