© 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. 22-RES-MATRYOSHKA-DC
    7. 2209
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to official rules, complaints and legal processes in a correctional facility

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     allerlei
    -0.84
     immerhin
    -0.81
     supposedly
    -0.74
     dodgy
    -0.73
    прочем
    -0.73
     Somehow
    -0.73
     stuff
    -0.71
     вроде
    -0.71
     Surely
    -0.70
     hardly
    -0.70
    POSITIVE LOGITS
     utilizing
    0.88
     prosím
    0.77
    utiliz
    0.69
     utilize
    0.69
     utilizes
    0.68
     ErrIntOverflow
    0.68
     Utilizing
    0.68
     utilized
    0.67
    TBD
    0.67
     Utilize
    0.66
    Activations Density 1.231%

    No Known Activations