© 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. 521
    Prev
    Next
    INDEX
    Explanations

    the word "family" along with related words

    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
    AndEndTag
    -0.75
    enumii
    -0.75
     ThemeData
    -0.69
     Magenta
    -0.69
     pinulongan
    -0.68
    Vidite
    -0.65
    enumi
    -0.65
    okovic
    -0.65
     ProtoMessage
    -0.65
     térmica
    -0.64
    POSITIVE LOGITS
     family
    1.07
     members
    1.06
     Family
    1.01
    Family
    0.90
    family
    0.90
     FAMILY
    0.89
    FAMILY
    0.88
    👪
    0.84
     member
    0.81
     familia
    0.80
    Activations Density 0.164%

    No Known Activations