© 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. 2602
    Prev
    Next
    INDEX
    Explanations

    the present tense form of the verb 'to be'.

    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
     NSCoder
    -0.76
    Hentet
    -0.69
    AnchorTagHelper
    -0.68
    こんな感じ
    -0.66
    jenige
    -0.63
    InjectAttribute
    -0.62
     olyan
    -0.60
     that
    -0.60
     something
    -0.59
     such
    -0.59
    POSITIVE LOGITS
     myſelf
    1.02
     leaſt
    0.93
     himſelf
    0.87
     themſelves
    0.87
     purpoſe
    0.84
     Anſ
    0.81
     hopefully
    0.79
     otherwise
    0.79
     cauſe
    0.78
     uſed
    0.77
    Activations Density 0.534%

    No Known Activations