© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 44
    Prev
    Next
    INDEX
    Explanations

    sentences where the author expresses subjective feelings with "I"

    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
     feroit
    -1.06
     auroit
    -1.05
     avoient
    -1.02
     étoit
    -1.00
     pouvoit
    -0.91
     mourut
    -0.91
     étoient
    -0.90
     enfans
    -0.88
     démocr
    -0.80
     réguli
    -0.77
    POSITIVE LOGITS
     spend
    1.32
     get
    1.23
     put
    1.16
     think
    1.12
     go
    1.09
     want
    1.07
     know
    1.07
     try
    1.06
     do
    1.05
     use
    1.01
    Activations Density 6.107%

    No Known Activations