© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 359
    Prev
    Next
    INDEX
    Explanations

    general adjectives and descriptive words about people, especially those with social status

    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
     eds
    -0.65
     défendre
    -0.64
     cilind
    -0.63
    Coaching
    -0.58
     craindre
    -0.57
    seamnă
    -0.56
     którzy
    -0.55
    ælp
    -0.53
     locos
    -0.53
     rentrée
    -0.53
    POSITIVE LOGITS
     person
    1.28
     guy
    1.03
     participant
    1.01
     member
    0.98
     woman
    0.96
     musician
    0.95
     người
    0.93
     performer
    0.91
     player
    0.90
     researcher
    0.90
    Activations Density 3.004%

    No Known Activations