© 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. 5592
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ignore" and its variations, indicating a focus on neglect or dismissal of certain information or responsibilities

    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
     oper
    -0.69
     jScrollPane
    -0.69
     snippetHide
    -0.67
    ResponseEntity
    -0.67
     Oper
    -0.66
    oper
    -0.61
    OPER
    -0.61
     OPER
    -0.59
     Rodgers
    -0.59
     CAMPBELL
    -0.59
    POSITIVE LOGITS
     ignored
    1.22
     ignore
    1.20
     ignores
    1.18
    glected
    1.16
    Ignored
    1.15
     disregarded
    1.15
     ignoring
    1.10
     Ignore
    1.09
    ignored
    1.09
     neglected
    1.05
    Activations Density 0.126%

    No Known Activations