© 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. 19696
    Prev
    Next
    INDEX
    Explanations

    terms related to analysis and assessment methodologies

    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
    ness
    -1.05
    er
    -0.98
    nya
    -0.88
    m
    -0.82
    nt
    -0.73
    r
    -0.71
    ner
    -0.71
    n
    -0.70
    ms
    -0.66
    mon
    -0.65
    POSITIVE LOGITS
     Theſe
    1.05
    ative
    1.05
     Houſe
    1.00
     myſelf
    0.99
     ſeveral
    0.97
    Kariera
    0.93
     themſelves
    0.93
    batore
    0.91
     ſmall
    0.89
     Diſ
    0.87
    Activations Density 0.113%

    No Known Activations