© 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. 391
    Prev
    Next
    INDEX
    Explanations

    the word "is" followed by words indicating something exists or can be considered

    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
    PYX
    -0.81
    GEBURTSDATUM
    -0.77
    AsUp
    -0.77
     propOrder
    -0.75
    Abitanti
    -0.75
     Meksiku
    -0.73
     <<<<<<<<<<<<<<
    -0.73
    oredCriteria
    -0.73
     Shakspeare
    -0.72
    complexType
    -0.69
    POSITIVE LOGITS
     no
    1.03
     plenty
    0.89
     a
    0.81
     some
    0.79
     lots
    0.70
    plenty
    0.68
     ample
    0.67
     NO
    0.65
     an
    0.65
     nothing
    0.63
    Activations Density 0.633%

    No Known Activations