© 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. 1779
    Prev
    Next
    INDEX
    Explanations

    subjective pronouns and clauses (I, it, that)

    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
     eredmény
    -0.50
    結果
    -0.47
    HtmlAttribute
    -0.46
     Folge
    -0.46
     péri
    -0.46
     mümkün
    -0.45
     can
    -0.44
     results
    -0.43
    Resultado
    -0.43
     faces
    -0.42
    POSITIVE LOGITS
     fascin
    1.03
     amaze
    1.00
     reminded
    0.98
     remind
    0.96
     amuse
    0.94
     excites
    0.90
     impressed
    0.89
     GenerationType
    0.88
     intrigued
    0.88
     appealed
    0.88
    Activations Density 1.050%

    No Known Activations