© 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. 1526
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to children's behavior and parenting

    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
     bastard
    -0.60
     bloke
    -0.58
     fucking
    -0.58
     mujer
    -0.57
    lwjgl
    -0.57
     vrouwen
    -0.55
    Damn
    -0.55
    inale
    -0.55
     Femmes
    -0.54
     fuckin
    -0.54
    POSITIVE LOGITS
     toys
    1.13
     playtime
    1.08
     preschool
    1.02
     Preschool
    1.01
     Toys
    1.01
     toy
    0.98
    Toys
    0.94
     play
    0.92
     playground
    0.90
     Mommy
    0.90
    Activations Density 1.691%

    No Known Activations