© 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. 2-RES-MATRYOSHKA-DC
    7. 2887
    Prev
    Next
    INDEX
    Explanations

    specific numerical values that are closest to a referenced number

    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
     far
    -1.06
    far
    -0.90
    Far
    -0.83
     Far
    -0.80
     FAR
    -0.79
    FAR
    -0.76
     distance
    -0.70
     OpenAPI
    -0.67
     DISTANCE
    -0.65
     afstand
    -0.64
    POSITIVE LOGITS
     nearest
    2.67
    nearest
    2.19
     Nearest
    1.88
    Nearest
    1.70
     closest
    1.49
     nearer
    1.04
     ближай
    1.02
    closest
    0.88
     nearby
    0.80
     nærm
    0.79
    Activations Density 0.019%

    No Known Activations