© 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. 24642
    Prev
    Next
    INDEX
    Explanations

    numerical data related to population growth and migration trends

    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
    chiff
    -0.50
     Mercu
    -0.49
    efel
    -0.47
     across
    -0.44
    Kaynakça
    -0.44
    ionato
    -0.44
    Sidenav
    -0.44
    inheit
    -0.43
     оборо
    -0.42
    спи
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.69
    featureID
    0.68
    tagext
    0.67
    SequentialGroup
    0.66
    fjspx
    0.63
    mobileqq
    0.59
     horloge
    0.57
    ">//
    0.57
    reloj
    0.55
     pageContext
    0.54
    Activations Density 0.015%

    No Known Activations