© 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. 18-RES-MATRYOSHKA-DC
    7. 489
    Prev
    Next
    INDEX
    Explanations

    sentences using the word "will" or discussing the future

    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.18.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.18.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
     akár
    -0.68
    phrine
    -0.63
    omir
    -0.61
     gjø
    -0.60
     could
    -0.59
    ◊
    -0.58
    ाहरण
    -0.58
    equalTo
    -0.57
    Schemes
    -0.57
     volna
    -0.57
    POSITIVE LOGITS
     likely
    0.87
    oughby
    0.84
    likely
    0.83
     Likely
    0.83
     soon
    0.81
    soon
    0.78
     seguramente
    0.78
    fully
    0.77
     bientôt
    0.77
     hopefully
    0.77
    Activations Density 1.051%

    No Known Activations