© 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. 17190
    Prev
    Next
    INDEX
    Explanations

    references to Iceland and its cultural or geographical context

    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
    Negative Logits
     hin
    -0.48
    نق
    -0.46
     conjugate
    -0.43
    CAPIT
    -0.43
    raten
    -0.43
     Too
    -0.43
    enn
    -0.40
     Twitter
    -0.40
    vna
    -0.40
    weich
    -0.40
    POSITIVE LOGITS
    ]")]
    0.84
    WriteTagHelper
    0.84
    ValueStyle
    0.81
    TestingModule
    0.80
    extAlignment
    0.79
     CreateTagHelper
    0.76
    featureID
    0.74
     Audiodateien
    0.72
    AntiForgeryToken
    0.71
     AspNetCore
    0.69
    Activations Density 0.165%

    No Known Activations