© 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. 1331
    Prev
    Next
    INDEX
    Explanations

    mentions of caring about something, or negative feelings

    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
    regarding
    -0.96
     relating
    -0.94
     regarding
    -0.91
     concerning
    -0.88
     Relating
    -0.88
     Regarding
    -0.87
     dotyczące
    -0.85
     Concerning
    -0.84
     dotyczą
    -0.84
    concer
    -0.77
    POSITIVE LOGITS
     about
    1.83
    About
    1.38
    about
    1.28
     About
    1.27
     ABOUT
    1.18
    約
    0.91
    ABOUT
    0.90
    约
    0.84
     bout
    0.75
     abou
    0.75
    Activations Density 0.394%

    No Known Activations