© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4913
    Prev
    Next
    INDEX
    Explanations

    the term "analogue" or similar variants, indicating a focus on analogs or analogies

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tetapi
    -0.65
    "):
    -0.65
     hinweg
    -0.63
    ='';
    -0.60
    batore
    -0.59
    __":
    -0.59
    tableFuture
    -0.59
    ktop
    -0.58
     birbir
    -0.58
    StoryboardSegue
    -0.58
    POSITIVE LOGITS
     analog
    3.28
     Analog
    3.23
    analog
    3.17
    Analog
    3.06
     analogue
    3.03
     analogs
    2.70
     analogues
    2.52
     analogous
    1.74
     analogy
    1.67
     analogies
    1.53
    Activations Density 0.008%

    No Known Activations