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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5723
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and liability issues

    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
     folks
    -0.52
     "..\..\..\
    -0.52
     vibe
    -0.50
     
    -0.50
     fridge
    -0.48
    Erreferentziak
    -0.47
    ે
    -0.47
    ça
    -0.47
    ρω
    -0.46
     flipped
    -0.46
    POSITIVE LOGITS
    findpost
    0.80
    ChildScrollView
    0.75
     stället
    0.75
    awakeFromNib
    0.69
    gevens
    0.68
     morire
    0.65
     appellants
    0.65
    unggulan
    0.63
     Daß
    0.63
    orianCalendar
    0.63
    Activations Density 1.007%

    No Known Activations