© 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. 22-RES-MATRYOSHKA-DC
    7. 2627
    Prev
    Next
    INDEX
    Explanations

    sentences that start with imperative verbs, specifically, "let's"

    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
     <<<<<<<<<<<<<<
    -0.81
    WireFormatLite
    -0.73
     snippetHide
    -0.72
    πάρχ
    -0.66
     nakalista
    -0.66
    CppMethod
    -0.65
     pageContext
    -0.64
    httphttps
    -0.63
    CopyWith
    -0.63
    runOn
    -0.61
    POSITIVE LOGITS
     assume
    0.69
     face
    0.69
     suppose
    0.69
     imagine
    0.66
    assume
    0.57
    假设
    0.57
     assumption
    0.56
    imagine
    0.55
     us
    0.54
     say
    0.54
    Activations Density 0.023%

    No Known Activations