© 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. 29702
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and interactions

    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
    fjspx
    -1.25
     kaarangay
    -1.17
    sizeCache
    -1.16
    djangoproject
    -1.05
     betweenstory
    -1.02
     resourceCulture
    -1.00
     Roskov
    -0.99
    awtextra
    -0.96
     estimés
    -0.94
     HasFactory
    -0.92
    POSITIVE LOGITS
     
    0.53
     very
    0.50
     marge
    0.48
    pand
    0.47
     also
    0.47
    sist
    0.46
     relative
    0.46
     zależy
    0.46
    .
    0.45
     und
    0.45
    Activations Density 0.188%

    No Known Activations