© 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. 22-RES-MATRYOSHKA-DC
    7. 2199
    Prev
    Next
    INDEX
    Explanations

    words related to authority figures and their actions

    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.22.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.22.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
    脚注の使い方
    -0.93
    はじめに
    -0.56
    OTROS
    -0.47
    답
    -0.47
    phrine
    -0.46
    +#+#
    -0.45
     inexperienced
    -0.45
     forgot
    -0.43
    djangoproject
    -0.43
     réponses
    -0.43
    POSITIVE LOGITS
     advocating
    1.01
     lobbying
    0.98
     protested
    0.98
     advocated
    0.96
     protes
    0.92
     advocate
    0.91
     voicing
    0.90
     Advoc
    0.90
     oppose
    0.90
     opposed
    0.87
    Activations Density 0.751%

    No Known Activations