Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 26809
    Prev
    Next
    INDEX
    Explanations

    instructions related to modifying test cases in software testing 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
     ‘
    -0.64
    WEBPACK
    -0.61
     maybe
    -0.57
    прочем
    -0.56
     OFDb
    -0.53
     '
    -0.52
    huge
    -0.50
    AndEndTag
    -0.50
     huge
    -0.49
    …
    -0.49
    POSITIVE LOGITS
     pleaſure
    1.30
     myſelf
    1.29
     houſe
    1.27
     purpoſe
    1.20
    ſelf
    1.16
     itſelf
    1.15
     ſtate
    1.14
     becauſe
    1.10
     ſche
    1.09
     uſe
    1.09
    Activations Density 0.153%

    No Known Activations