© 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. 12-RES-MATRYOSHKA-DC
    7. 26510
    Prev
    Next
    INDEX
    Explanations

    instances of "parents" and "parental involvement."

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fathers
    -0.88
     Fathers
    -0.81
    fathers
    -0.76
    father
    -0.74
     pères
    -0.73
     endblock
    -0.73
     Father
    -0.71
     Czer
    -0.71
     father
    -0.71
    Father
    -0.70
    POSITIVE LOGITS
    PerformLayout
    0.72
     TextAppearance
    0.71
    UrlResolution
    0.70
     vPvB
    0.68
     personales
    0.64
     Irvine
    0.64
     couple
    0.63
    InitVars
    0.63
    Amin
    0.62
    ので
    0.61
    Activations Density 0.015%

    No Known Activations