© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5056
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to algebraic structures

    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
    ēju
    -0.51
     meglio
    -0.50
     mapStateToProps
    -0.49
     dipende
    -0.47
    داية
    -0.46
     hyö
    -0.45
     partecipa
    -0.44
    是多少
    -0.44
     vähän
    -0.44
     melhor
    -0.44
    POSITIVE LOGITS
    expandindo
    0.74
    LLocation
    0.73
     виправивши
    0.72
     tartalomajánló
    0.68
    +#+#
    0.68
     betweenstory
    0.68
    parsedMessage
    0.67
     bezeichneter
    0.65
    oredCriteria
    0.65
    MemoryWarning
    0.60
    Activations Density 0.889%

    No Known Activations