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. 383
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical proofs and structures in scientific 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
    bootstrapcdn
    -0.81
     InputDecoration
    -0.71
    SequentialGroup
    -0.70
     BoxDecoration
    -0.69
    ContentAlignment
    -0.69
    cdnjs
    -0.68
    databind
    -0.66
    AndEndTag
    -0.66
     صوتيه
    -0.66
     onAnimation
    -0.65
    POSITIVE LOGITS
    expandindo
    1.23
     CanadaChoose
    0.80
    afficheront
    0.75
    IVEREF
    0.73
    
    0.72
     betweenstory
    0.71
    osoba
    0.71
    abestanden
    0.70
    RegressionTest
    0.69
     Савезне
    0.69
    Activations Density 22.001%

    No Known Activations