© 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. 15426
    Prev
    Next
    INDEX
    Explanations

    actions and verbs related to tasks or commands

    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
     houſe
    -1.05
     ſtate
    -1.03
     myſelf
    -1.02
     purpoſe
    -0.97
     pleaſure
    -0.95
     poffe
    -0.92
     itſelf
    -0.92
     Jefus
    -0.91
     fubject
    -0.91
     perſon
    -0.91
    POSITIVE LOGITS
    矶
    0.75
     be
    0.69
     
    0.67
    icoot
    0.65
    ETHING
    0.64
     “
    0.63
    "]=
    0.62
    "]="
    0.60
     stel
    0.58
    ENOS
    0.57
    Activations Density 0.034%

    No Known Activations