© 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. 18511
    Prev
    Next
    INDEX
    Explanations

    terms related to positional and operational parameters in technical contexts

    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
     Schell
    -0.79
     Brice
    -0.76
     Pharmaco
    -0.74
     NKC
    -0.72
     Cleary
    -0.71
     Devine
    -0.70
    葩
    -0.70
    dentist
    -0.70
    
    -0.69
     König
    -0.69
    POSITIVE LOGITS
     стаття
    0.78
    ational
    0.75
     eventdata
    0.75
     Luf
    0.73
     ujednoznacz
    0.71
    al
    0.70
    lational
    0.69
    CLAIMER
    0.66
    alala
    0.65
    RTEX
    0.64
    Activations Density 0.056%

    No Known Activations