© 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. 23732
    Prev
    Next
    INDEX
    Explanations

    references to specific physical elements or structures

    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
    farin
    -0.52
    swick
    -0.50
    Билгалдахарш
    -0.50
     affiliate
    -0.50
     Réponses
    -0.49
     обстоя
    -0.49
    
    -0.49
     referido
    -0.47
     frequenza
    -0.46
    ürd
    -0.46
    POSITIVE LOGITS
     zitten
    0.73
     enthalten
    0.60
    τώ
    0.57
     Contains
    0.56
     contains
    0.55
     contain
    0.54
     iprot
    0.53
    اوية
    0.53
    Portály
    0.52
     Référence
    0.51
    Activations Density 0.153%

    No Known Activations