© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11524
    Prev
    Next
    INDEX
    Explanations

    repeated references to elements that indicate content omission or abstraction

    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
     <<<<<<<<<<<<<<
    -0.68
     even
    -0.50
     balanced
    -0.49
    orElseThrow
    -0.49
    smarty
    -0.48
     Профиль
    -0.48
     Balanced
    -0.47
    even
    -0.46
    PickerController
    -0.45
    干
    -0.45
    POSITIVE LOGITS
    NameInMap
    0.66
    AndEndTag
    0.66
     оригіналу
    0.65
     nakalista
    0.65
    DispatchToProps
    0.63
    Hentet
    0.63
    itares
    0.60
     intptr
    0.59
     estekak
    0.58
    Durée
    0.58
    Activations Density 0.004%

    No Known Activations