© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17631
    Prev
    Next
    INDEX
    Explanations

    terms related to parental engagement in educational or health interventions

    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
    #}
    -0.39
    arova
    -0.39
     stepped
    -0.39
    ści
    -0.39
    amai
    -0.37
    ObjectContext
    -0.37
    orum
    -0.35
    ietic
    -0.35
    jst
    -0.35
    sc
    -0.35
    POSITIVE LOGITS
     nakalista
    1.04
     endwhile
    0.75
     newBuilder
    0.73
    ValueStyle
    0.72
     doInBackground
    0.71
    QMetaType
    0.70
    tanleria
    0.69
    ErrUnexpectedEOF
    0.68
    wpi
    0.65
    setVerticalGroup
    0.65
    Activations Density 0.385%

    No Known Activations