© 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. 5149
    Prev
    Next
    INDEX
    Explanations

    statements that describe the extent or degree of a comparison or difference

    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
     distance
    -1.17
     Distance
    -1.10
    distance
    -1.05
    Distance
    -1.02
     DISTANCE
    -0.96
     distances
    -0.94
     distancia
    -0.92
    nearest
    -0.91
    DISTANCE
    -0.88
     nearest
    -0.86
    POSITIVE LOGITS
     far
    2.72
    far
    2.36
    Far
    2.09
     Far
    1.98
     FAR
    1.82
    FAR
    1.79
     langt
    1.24
     jauh
    1.20
     далеко
    1.15
     daleko
    1.13
    Activations Density 0.021%

    No Known Activations