© 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. 14032
    Prev
    Next
    INDEX
    Explanations

    specific statistics or metrics related to performance and timing

    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
    الحياه
    -0.82
    principalTable
    -0.78
    Hahahahaha
    -0.71
    apimachinery
    -0.70
    GEBURTSDATUM
    -0.69
    bewerken
    -0.67
     ivelany
    -0.62
    nezeu
    -0.61
     puissiez
    -0.60
    CodedInputStream
    -0.60
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
    ViewImports
    0.61
    醐
    0.59
     arşivlendi
    0.55
     viewType
    0.54
     Colón
    0.50
     GIP
    0.49
    GOM
    0.48
     Dud
    0.47
     wirk
    0.47
    Activations Density 0.032%

    No Known Activations