© 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. 30005
    Prev
    Next
    INDEX
    Explanations

    specific names associated with personal narratives or notable individuals

    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
    verständlich
    -0.69
    providedIn
    -0.62
     الدولى
    -0.56
    HostException
    -0.55
    NewUrlParser
    -0.50
    cshtml
    -0.49
    OnClickListener
    -0.48
     ویکی‌پدیا
    -0.48
    ==============
    -0.47
    TimerTask
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.60
     <<<<<<<<<<<<<<
    0.55
     pescoço
    0.55
    enya
    0.53
    Sectors
    0.53
     Numerade
    0.52
     protoimpl
    0.52
     transfieras
    0.52
     unknownFields
    0.52
     Baillar
    0.52
    Activations Density 0.522%

    No Known Activations