© 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. 376
    Prev
    Next
    INDEX
    Explanations

    instances of encouraging phrases or concepts that involve helping or directing a person

    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
     faisons
    -0.54
    ')->
    -0.49
    medriver
    -0.48
    在我的
    -0.47
    在我
    -0.46
     mich
    -0.45
     moje
    -0.45
    让我们
    -0.44
     jestem
    -0.44
    cheibe
    -0.44
    POSITIVE LOGITS
     you
    3.64
    you
    2.45
    You
    2.05
     você
    2.03
     YOU
    2.02
     You
    1.96
     vous
    1.96
     your
    1.77
     شما
    1.69
     вам
    1.68
    Activations Density 2.453%

    No Known Activations