© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    internet slang and emotional expressions

    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
     CURLOPT
    -0.51
     Congressman
    -0.49
     \$
    -0.48
     vård
    -0.47
    ということ
    -0.47
    guía
    -0.46
     "
    -0.44
    ↓
    -0.44
     Obispo
    -0.44
    igné
    -0.43
    POSITIVE LOGITS
     youll
    1.90
     theyre
    1.84
     theres
    1.80
    Theres
    1.77
     shes
    1.77
     Theres
    1.74
     thats
    1.71
     dont
    1.70
    Dont
    1.69
     youre
    1.68
    Activations Density 0.575%

    No Known Activations