© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    question words followed by a pronoun

    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
    DockStyle
    -0.64
    σιμοποι
    -0.56
     consultato
    -0.53
    RunWith
    -0.52
    raszamy
    -0.51
    setVerticalGroup
    -0.50
     TAMBÉM
    -0.49
    sidemargin
    -0.49
    contentLoaded
    -0.49
    водства
    -0.49
    POSITIVE LOGITS
     doing
    1.13
     accomplish
    1.02
    Doing
    0.96
     Doing
    0.96
     done
    0.94
     do
    0.93
    doing
    0.93
     DOING
    0.90
     accomplished
    0.84
     doin
    0.84
    Activations Density 0.522%

    No Known Activations