© 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. 31101
    Prev
    Next
    INDEX
    Explanations

    terms related to workshops and educational events focused on various subjects, particularly social media and drug awareness

    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
     rest
    -0.54
     en
    -0.51
    qui
    -0.44
     di
    -0.44
     '
    -0.43
     et
    -0.43
    ாவ
    -0.42
    googleapis
    -0.42
     empe
    -0.41
    essége
    -0.41
    POSITIVE LOGITS
    AccessorTable
    0.96
     Jefus
    0.90
     myſelf
    0.90
    setVerticalGroup
    0.86
     Efq
    0.86
    BeginInit
    0.83
     raiſ
    0.82
    MessageTagHelper
    0.82
     poffible
    0.81
     fhort
    0.79
    Activations Density 0.114%

    No Known Activations