© 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. 29768
    Prev
    Next
    INDEX
    Explanations

    phrases related to elections and political candidacy

    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
    enumi
    -0.69
    存于互联网档案馆
    -0.68
    enumii
    -0.57
    ContentAlignment
    -0.56
    PASSED
    -0.55
     pat
    -0.54
    elux
    -0.53
     people
    -0.52
    TypedDataSet
    -0.51
    LookAnd
    -0.50
    POSITIVE LOGITS
     démocr
    0.82
     peindre
    0.76
     purpoſe
    0.73
     uſe
    0.73
    ReusableCell
    0.71
     säll
    0.70
     Bewußt
    0.69
     Majefty
    0.69
     fubject
    0.69
     preescolar
    0.66
    Activations Density 0.104%

    No Known Activations