© 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. 104
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes, particularly in technical and systematic 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
     Houſe
    -0.81
     يتيمه
    -0.80
     Jefus
    -0.79
     Chriftian
    -0.79
     auffi
    -0.76
     Chriſt
    -0.75
     Chrift
    -0.73
     Theſe
    -0.73
     Monfieur
    -0.72
     privatisation
    -0.72
    POSITIVE LOGITS
     but
    1.23
     however
    1.20
     and
    1.17
     which
    1.11
     although
    1.11
     including
    1.00
     though
    0.94
     while
    0.94
     especially
    0.91
     or
    0.89
    Activations Density 3.795%

    No Known Activations