© 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. 9793
    Prev
    Next
    INDEX
    Explanations

    references to historical and political contexts, particularly related to rulers and governance

    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
     Hernando
    -0.58
    tanleria
    -0.56
     polaroid
    -0.54
     vario
    -0.54
     brut
    -0.53
    equals
    -0.52
     Sando
    -0.52
    OGND
    -0.51
    ագրություն
    -0.51
     HttpHeaders
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.71
    AndroidJUnit
    0.64
    yors
    0.54
    IsContent
    0.54
    IVEREF
    0.54
    }]
    0.53
    joc
    0.53
    /></
    0.50
     seat
    0.49
    }],
    0.49
    Activations Density 0.224%

    No Known Activations