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. 30188
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to the medical and scientific fields

    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
    ftagPool
    -0.73
     lenker
    -0.71
    Geplaatst
    -0.69
    Хьажоргаш
    -0.64
    SBATCH
    -0.63
    WithIOException
    -0.61
    DebuggerStep
    -0.60
     Superhost
    -0.59
    Сылтамалар
    -0.58
     Normdatei
    -0.57
    POSITIVE LOGITS
    autoIncrement
    0.63
    Actual
    0.58
     actual
    0.57
    実際に
    0.54
     Actual
    0.54
     сами
    0.51
    arko
    0.51
    tista
    0.50
    実際の
    0.49
    ParallelGroup
    0.49
    Activations Density 0.908%

    No Known Activations