© 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. 9728
    Prev
    Next
    INDEX
    Explanations

    terms related to forfeiture and legal liability

    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
    swick
    -0.75
    iddler
    -0.69
    OpenHelper
    -0.69
     dysplasia
    -0.68
    inquirer
    -0.68
     couverts
    -0.66
    entiated
    -0.64
    cuad
    -0.63
    innung
    -0.63
     Shade
    -0.63
    POSITIVE LOGITS
     forfeiture
    1.48
     forfe
    1.08
     forfeited
    1.07
     forfeit
    0.93
    SharedCtor
    0.63
    AndEndTag
    0.62
     Toko
    0.61
     useRouter
    0.59
    iture
    0.58
     صوتيه
    0.56
    Activations Density 0.001%

    No Known Activations