© 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. 11546
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a specific license statement

    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
     utafitiHapana
    -0.84
    CloseOperation
    -0.81
     linkovi
    -0.68
     ProtoMessage
    -0.65
    ftagPool
    -0.65
    toggler
    -0.65
    djangoproject
    -0.60
    sizeCache
    -0.60
    újo
    -0.60
    jface
    -0.60
    POSITIVE LOGITS
    ſelves
    0.56
    نیم
    0.50
     poffe
    0.49
    ſelf
    0.48
     odkazy
    0.47
     ſhould
    0.47
     noft
    0.47
     ſta
    0.47
     purpoſe
    0.46
    Indented
    0.45
    Activations Density 0.002%

    No Known Activations