© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25914
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complaint" in various forms

    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
    Negative Logits
     calitate
    -0.66
    es
    -0.59
    Diva
    -0.57
     Aseg
    -0.57
     fapt
    -0.54
     tu
    -0.54
     ويكيميديا
    -0.54
     Fara
    -0.54
    III
    -0.53
    ε
    -0.53
    POSITIVE LOGITS
    uxxxx
    0.93
    FormTagHelper
    0.91
    VersionUID
    0.81
     Normdatei
    0.80
    HostException
    0.76
     kasarigan
    0.74
    ksikon
    0.74
    mybatisplus
    0.71
     ComVisible
    0.71
    TagHelper
    0.71
    Activations Density 0.007%

    No Known Activations