© 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. 920
    Prev
    Next
    INDEX
    Explanations

    This neuron is looking for language related to books and romance novels, especially marketing or promotional material.

    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
    SharedDtor
    -0.75
     protoimpl
    -0.74
     footage
    -0.72
    SequentialGroup
    -0.71
    DebuggerNonUser
    -0.69
    Datuak
    -0.66
    UnknownFields
    -0.63
    曖昧さ回避
    -0.63
     Footage
    -0.60
    writeFieldEnd
    -0.59
    POSITIVE LOGITS
     novels
    1.28
     books
    1.26
     book
    1.23
     author
    1.15
     authors
    1.11
     Goodreads
    1.09
     novel
    1.07
     Author
    1.03
    books
    1.03
    Author
    1.02
    Activations Density 1.076%

    No Known Activations