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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22576
    Prev
    Next
    INDEX
    Explanations

    the word "it" across various 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
     تانيه
    -0.80
    脚注の使い方
    -0.73
    ftagPool
    -0.71
    HideFlags
    -0.67
     AssemblyVersion
    -0.66
    rzost
    -0.66
     télécharge
    -0.65
     fatica
    -0.65
     hjär
    -0.64
     SafeMath
    -0.64
    POSITIVE LOGITS
    英語版
    0.59
     be
    0.58
    huk
    0.56
    fromnode
    0.56
     consist
    0.55
    tituto
    0.55
    ,:)
    0.55
     conto
    0.53
     DbType
    0.50
     itself
    0.49
    Activations Density 0.095%

    No Known Activations