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. 15726
    Prev
    Next
    INDEX
    Explanations

    biological terms related to cancer and growth factors

    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
     utafitiHapana
    -0.60
     áll
    -0.54
    AsStream
    -0.52
     ihren
    -0.48
     adipis
    -0.47
     varanda
    -0.47
     vor
    -0.47
     consciência
    -0.46
    TypedDataSet
    -0.45
    üttel
    -0.45
    POSITIVE LOGITS
     EGFR
    1.16
    ValueStyle
    1.01
    inib
    0.93
    SequentialGroup
    0.91
    ]--;
    0.83
     للاسماء
    0.82
    awtextra
    0.80
     EconPapers
    0.77
     autorytatywna
    0.76
     footh
    0.74
    Activations Density 0.016%

    No Known Activations