© 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. 2381
    Prev
    Next
    INDEX
    Explanations

    references to accountability and previous behavior patterns

    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
    CodedInputStream
    -0.67
     متعلقه
    -0.62
    fromCharCode
    -0.60
    wegg
    -0.59
    ksessa
    -0.56
    esterday
    -0.54
     mouseY
    -0.54
    GetAsync
    -0.54
    theless
    -0.54
    DataAnnotations
    -0.54
    POSITIVE LOGITS
     previous
    1.05
    Previous
    0.88
    previous
    0.88
     Previous
    0.84
     previously
    0.83
     precedent
    0.83
     precedenti
    0.76
     tidigare
    0.72
     PREVIOUS
    0.72
    PREVIOUS
    0.71
    Activations Density 0.493%

    No Known Activations