© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 21581
    Prev
    Next
    INDEX
    Explanations

    terms related to penalties and their relief in taxation 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
     doInBackground
    -0.78
     répondu
    -0.71
     ricordi
    -0.68
     gefällt
    -0.67
     AssemblyCulture
    -0.66
    jLabel
    -0.63
     TreeMap
    -0.62
     Compens
    -0.62
    \{\\
    -0.61
     recommandons
    -0.61
    POSITIVE LOGITS
     penalty
    1.09
    penalty
    1.06
     Penalty
    0.98
     penalties
    0.94
    Penalty
    0.91
     Penalties
    0.87
    ALTY
    0.82
    alties
    0.82
    AndEndTag
    0.74
     Ellison
    0.73
    Activations Density 0.003%

    No Known Activations