© 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. 31063
    Prev
    Next
    INDEX
    Explanations

    references to liabilities and damages in legal or software-related contexts

    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
    RTDA
    -0.70
     Himo
    -0.61
     useHistory
    -0.55
     propOrder
    -0.54
     himo
    -0.53
     arşivlendi
    -0.51
    슷
    -0.49
    jsxFileName
    -0.49
     sporo
    -0.48
    Reported
    -0.47
    POSITIVE LOGITS
     DAMAGES
    2.66
     damages
    1.52
     Damages
    1.45
    Dama
    1.04
     Damage
    0.87
     damage
    0.84
     DAMAGE
    0.81
     dommages
    0.81
     للمعارف
    0.80
     daños
    0.75
    Activations Density 0.000%

    No Known Activations