© 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. 20395
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal history and offender classifications

    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
     <",
    -0.89
    WaitGroup
    -0.84
    MLLoader
    -0.75
    LookAnd
    -0.74
     linkovi
    -0.69
     InputDecoration
    -0.69
    IntoConstraints
    -0.68
     ffilmiau
    -0.68
     gawas
    -0.68
     nakalista
    -0.68
    POSITIVE LOGITS
     թվական
    0.45
    /******/
    0.42
    ondata
    0.41
     refor
    0.40
    ingu
    0.39
    دانشنامهٔ
    0.39
    日
    0.39
     rhum
    0.38
    bial
    0.38
     l
    0.38
    Activations Density 0.029%

    No Known Activations