© 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. 2760
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people in a context related to news reporting

    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
    rungsseite
    -0.71
     himself
    -0.65
     solo
    -0.59
    solo
    -0.59
    一人で
    -0.52
     själv
    -0.52
     Himself
    -0.51
    /**
    -0.50
    Kanpo
    -0.49
    himself
    -0.47
    POSITIVE LOGITS
     gathered
    1.35
     flock
    1.18
     congreg
    1.17
     flocked
    1.16
     crowding
    1.12
     gathers
    1.07
     assembled
    1.06
     gather
    1.05
     clustered
    1.02
     throng
    0.98
    Activations Density 0.622%

    No Known Activations