© 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. 18-RES-MATRYOSHKA-DC
    7. 700
    Prev
    Next
    INDEX
    Explanations

    the word "civil"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     itſelf
    -0.91
    RetentionPolicy
    -0.87
     Monfieur
    -0.83
     auffi
    -0.82
    ſelves
    -0.82
     doubtnut
    -0.82
     becauſe
    -0.81
     bezeichneter
    -0.80
    ็จ
    -0.80
     $_"
    -0.79
    POSITIVE LOGITS
     civil
    1.32
     Civil
    1.26
    Civil
    1.14
    civil
    1.10
     CIVIL
    1.00
    CIV
    0.80
     civi
    0.73
     civ
    0.72
     Civ
    0.72
     Zivil
    0.69
    Activations Density 0.027%

    No Known Activations